WO2024040797A1

WO2024040797A1 - Electroencephalogram-based autism evaluation apparatus and method, terminal device, and medium

Info

Publication number: WO2024040797A1
Application number: PCT/CN2022/137707
Authority: WO
Inventors: 尉增杰; 王怡珊; 徐永杰; 李烨
Original assignee: 深圳先进技术研究院
Priority date: 2022-08-26
Filing date: 2022-12-08
Publication date: 2024-02-29
Also published as: CN115414041A

Abstract

An electroencephalogram-based autism evaluation apparatus (600) and method, a terminal device (7), and a medium. The electroencephalogram-based autism evaluation apparatus (600) specifically comprises: an acquisition unit (601) used for acquiring first electroencephalogram of a whole brain region of an object to be evaluated, the first electroencephalogram comprising second electroencephalogram of a plurality of channels; a determination unit (602) used for determining a brain connection image according to the first electroencephalogram, the brain connection image being used for representing the degree of association between the second electroencephalogram of each two of the plurality of channels; and an evaluation unit (603) used for determining an autism evaluation result of the object to be evaluated according to the brain connection image. Therefore, the brain connection image is used as a reference and the accuracy of the autism evaluation result is improved.

Description

Autism assessment device, method, terminal equipment and medium based on EEG data

Technical field

The present application belongs to the field of signal processing technology, and in particular relates to an autism assessment device, method, terminal equipment and readable storage medium based on EEG data.

Background technique

Autism spectrum disorder is a widespread neurodevelopmental disorder whose main symptoms include social communication impairment, language communication impairment, and repetitive stereotyped behaviors. Electroencephalogram (EEG) has the advantages of low cost, non-invasiveness, high temporal resolution, and is relatively subject-friendly during the signal collection process. It is currently an effective method for detecting autism. Way. At present, the assessment of autism mainly relies on doctors' interpretation and judgment of EEG data, which requires doctors to have a high professional level and has low diagnostic efficiency. Moreover, as a kind of raw data, EEG data has low physiological interpretability for the assessment of autism, and the accuracy of autism assessment results based on the amplitude or initial characteristics of EEG data is low.

technical problem

Embodiments of the present application provide an autism assessment device, method, terminal device and readable storage medium based on EEG data, which can solve the current problem of low accuracy of autism assessment results.

Technical solutions

The first aspect of the embodiment of the present application provides an autism assessment device based on EEG data, including: an acquisition unit for acquiring first EEG data of the entire brain area of the subject to be evaluated, the first EEG data including second EEG data of a plurality of channels; a determining unit configured to determine a brain connectivity image according to the first EEG data, the brain connectivity image being used to characterize the two channels of each of the plurality of channels; The degree of correlation between the second EEG data; an evaluation unit configured to determine the autism evaluation result of the subject to be evaluated based on the brain connectivity image.

The second aspect of the embodiments of the present application provides an autism assessment method based on EEG data, including: obtaining first EEG data of the entire brain area of the subject to be evaluated, where the first EEG data includes multiple channels. second EEG data; determining a brain connectivity image according to the first EEG data, the brain connectivity image being used to represent the degree of correlation between the second EEG data of each two channels in the plurality of channels ; Determine the autism assessment result of the subject to be assessed based on the brain connectivity image.

The third aspect of the embodiment of the present application provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above is implemented. Functionality of an autism assessment device based on EEG data.

The fourth aspect of the embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the above-mentioned autism assessment device based on EEG data is implemented. Function.

The fifth aspect of the embodiments of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device implements the function of the autism assessment device based on EEG data described in the first aspect.

beneficial effects

In an embodiment of the present application, the first EEG data of the whole brain area of the subject to be evaluated is obtained, the brain connectivity image is determined based on the first EEG data, and the autism assessment of the subject to be assessed is determined based on the brain connectivity image. As a result, on the one hand, referring to the first EEG data of the whole brain area can avoid missing the more important EEG information of some brain areas. On the other hand, the first EEG data includes multiple channels of second EEG data. The connectivity image can be used to characterize the degree of correlation between the second EEG data of each two channels in multiple channels. This degree of correlation can characterize the correlation between the brain functions of the corresponding channels and reflect the exchange and integration of information between brain areas. These abilities are related to the social, language and behavioral difficulties of the subject to be assessed. Therefore, using the brain connectivity image as a reference, the autism assessment results obtained are physiologically interpretable and more accurate.

fruit value

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the purpose of the present application. For some embodiments, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting creative efforts.

Figure 1 is a schematic flow chart of the implementation of an autism assessment method based on EEG data provided by an embodiment of the present application;

Figure 2 is a schematic diagram of EEG data provided by an embodiment of the present application;

Figure 3 is a brain connectivity diagram of an autistic patient provided by an embodiment of the present application;

Figure 4 is a brain connectivity diagram of normal people provided by the embodiment of the present application;

Figure 5 is a schematic structural diagram of the autism classification model provided by the embodiment of the present application;

Figure 6 is a schematic structural diagram of an autism assessment device based on EEG data provided by an embodiment of the present application;

Figure 7 is a schematic structural diagram of a terminal device provided by an embodiment of the present application.

Embodiments of the invention

In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without any creative work shall belong to the protection of this application.

At present, the assessment of autism mainly relies on doctors' interpretation and judgment of EEG data, which requires doctors to have a high professional level and has low diagnostic efficiency. Some related technologies convert EEG data into spectrogram images, design hybrid deep lightweight feature generators for initial feature extraction, and then use Support Vector Machine (SVM) classifiers for classification after filtering features. Alternatively, texture features are extracted through traditional machine learning methods and classified using machine learning classifiers. However, as a kind of raw data, EEG data can only represent the information of the corresponding brain area. For the assessment of autism, the physiological interpretability is low. The amplitude or initial features (texture features) of the EEG data are based on The autism assessment results produced are less accurate.

To this end, this application provides an autism assessment method based on EEG data, which uses EEG data from the entire brain region to generate brain connectivity images that represent the degree of correlation between EEG data from different channels. The degree of correlation between EEG data can represent the correlation between the brain functions of the corresponding brain areas of the subject to be assessed, and reflect the ability to communicate and integrate information between brain areas. These abilities are related to the social interaction, language and behavior of the subject to be assessed. Therefore, using the brain connectivity image as a reference, the autism assessment results given are physiologically interpretable and more accurate.

In order to illustrate the technical solution of the present application, specific embodiments are provided below.

Figure 1 shows a schematic flow chart of the implementation of an autism assessment method based on EEG data provided by an embodiment of the present application. This method can be applied to terminal devices and can be applied to situations where the accuracy of autism assessment results needs to be improved. situation. Among them, the above-mentioned terminal devices can be smart devices such as computers, smartphones, tablets, etc., or they can also be special devices used to assess the risk of autism.

Specifically, the above-mentioned autism assessment method may include the following steps S101 to S103.

Step S101: Obtain first EEG data of the entire brain area of the subject to be evaluated.

In the embodiment of the present application, the object to be evaluated may refer to a person or animal that needs to be evaluated for autism. In order to determine the correlation between the EEG data, the above-mentioned first EEG data may include second EEG data of multiple channels of the subject to be evaluated.

In some embodiments of the present application, the terminal device may be configured with a collection device for collecting EEG data, and the collection device may be an embedded or non-embedded device. In order to make the experience of the object to be evaluated better, the collection transposition can choose a non-embedded collection device. Specifically, the non-embedded collection device may refer to electrode sheets, and each electrode sheet may be disposed non-overlappingly outside the cerebral cortex of the subject to be evaluated. These electrodes placed outside the cerebral cortex are called active electrodes and can be used to collect the potential difference between them and the reference electrode as EEG data. The reference electrode is generally placed on the body as an electrode with relative zero potential. The EEG data collected by each active electrode is the EEG data of one channel, and then the terminal device can obtain the second EEG data collected by the electrode sheet that corresponds one-to-one to each of the multiple channels, forming a complete The first EEG data of the brain region. Of course, in other implementations, the terminal device can also obtain the first EEG data through other methods, for example, the user can input the first EEG data obtained by pre-testing the subject to be evaluated, etc.

The first EEG data and the second EEG data may specifically refer to frequency-amplitude data, or time-amplitude data. Figure 2 shows a schematic diagram of two types of time-amplitude data.

In embodiments of the present application, multiple channels can be used to characterize the entire brain area of the subject to be evaluated, and the second EEG data of each channel in the multiple channels can be used to characterize the brain function of the corresponding brain area. Brain areas are also brain functional divisions, which can include the brainstem, parietal lobe, frontal lobe, etc. Specifically, in this application, multiple may refer to at least two. In order to characterize the entire brain area of the subject to be evaluated, the number of channels selected is generally eight or more. Preferably, in order to ensure the reliability of the evaluation results, The number of channels of the second EEG data collected may be 125 or more. In this way, the electrode sheet can completely or nearly completely cover the outside of the cerebral cortex of the subject to be evaluated. Thus, the data of the subject to be assessed can be collected. The first EEG data of the whole brain region. The second EEG data of each channel can represent the signal generated by the brain area where the corresponding electrode patch is located, and thus can represent part or all of the brain functions of the corresponding brain area.

In order to facilitate subsequent evaluation, the terminal device can also perform routine preprocessing operations on the collected EEG data, and save the EEG data obtained after the preprocessing operation as EEG data for autism assessment. . Among them, preprocessing operations include but are not limited to filtering processing, baseline removal processing and noise removal processing. Filtering processing can include high-pass filtering and low-pass filtering, and combined with baseline removal processing can remove noise such as burrs in the EEG data. Noise removal processing can be used to remove noise such as electrooculoscopy and electromyography, which can avoid the impact of irrelevant physiological signals on EEG data.

Step S102: Determine the brain connectivity image based on the first EEG data.

In embodiments of the present application, the brain connectivity image may be used to characterize the degree of correlation between the second EEG data of each two channels in the plurality of channels. The correlation degree of the second EEG data between each two channels also represents the connectivity between the brain functions represented by the two channels.

Specifically, the terminal device can determine the degree of correlation between the second EEG data of each two channels in the multiple channels, and determine the pixel value of the pixel point at each position in the brain connectivity image according to the degree of correlation, to obtain the brain connectivity image.

Among them, the degree of correlation can be calculated using statistical methods that represent correlations. For example, Spearman’s rank correlation coefficient, Pearson correlation coefficient can be used. coefficient), Kendall correlation coefficient, etc. Among them, the Pearson correlation coefficient is a linear correlation coefficient, which is the most commonly used correlation coefficient. It can be used to reflect the linear correlation degree of the sum of two variables. The obtained value is between -1 and 1, and its absolute value is between -1 and 1. Larger values indicate stronger correlation.

Specifically, the terminal device can calculate the correlation degree of the second EEG data between the two channels through the following formula: .

Among them, r represents the correlation degree of the second EEG data between the x channel and the y channel, and the x channel and the y channel are any one of the multiple channels respectively. n represents the length of the time series, and i represents the sampling moment. x _i represents the amplitude of the second EEG data of channel x at the i-th sampling moment, Indicates the average value of the amplitude of the second EEG data of the x channel at n sampling moments. y _i represents the amplitude of the second EEG data of the y channel at the i-th sampling moment, Indicates the average value of the amplitude of the second EEG data of the y channel at n sampling moments.

The brain connectivity image can be an image composed of M×M pixels, where M is equal to the total number of channels included in the first EEG data. Using the degree of correlation between each two channels, the pixel values of the pixels corresponding to the two channels in the brain connectivity image can be determined to obtain the brain connectivity image. Taking 125 channels as an example, by calculating the degree of correlation between channels, the connectivity between brain functions represented by each channel can be quantified, and a 125×125 functional connection matrix can be obtained. Using the degree of correlation between the first channel and the second channel, the pixel value of the pixel in row 1 and column 2 and the pixel value of the pixel in row 2 and column 1 in the brain connectivity image can be determined. By analogy, the pixel value of the pixel point at each position can be obtained. Furthermore, a 125×125 brain connectivity image is generated from the pixel values of pixels at each position.

Step S103: Determine the autism assessment result of the subject to be assessed based on the brain connectivity image.

Among them, the autism assessment result is the assessment result of the autism risk level of the subject to be assessed.

In some embodiments of the present application, the terminal device can pre-train the autism classification model, input the brain connectivity image to the trained autism classification model, and obtain the autism assessment results output by the autism classification model.

In other embodiments, the brain connectivity image can also be compared with the brain connectivity image corresponding to the normal population. If the difference between the brain connectivity image and the brain connectivity image reaches a preset difference threshold, the evaluation to be evaluated can be confirmed. The subject was assessed as being at high risk for autism. Otherwise, it can be confirmed that the autism assessment result of the subject to be evaluated is low autism risk. Of course, considering that subjects to be evaluated at different ages may have different performances on the brain connectivity images, the brain connectivity images can also be compared with the corresponding brain connectivity images of normal people of the same age to obtain autism assessment results.

It should be understood that no matter which method is used, as long as the autism assessment result is determined through brain connectivity images based on EEG signals, it falls within the scope of protection of this application.

In an embodiment of the present application, the first EEG data of the whole brain area of the subject to be evaluated is obtained, the brain connectivity image is determined based on the first EEG data, and the autism assessment of the subject to be assessed is determined based on the brain connectivity image. As a result, on the one hand, referring to the first EEG data of the whole brain area can avoid missing the more important EEG information of some brain areas. On the other hand, the first EEG data includes multiple channels of second EEG data. The connected image can be used to characterize the degree of correlation between the second EEG data of each two channels in multiple channels. This degree of correlation can characterize the correlation between brain functions in the corresponding brain areas and reflect the exchange and integration of information between brain areas. These abilities are related to the social, language and behavioral difficulties of the subject to be assessed. Therefore, using the brain connectivity image as a reference, the autism assessment results obtained are physiologically interpretable and more accurate.

The evaluation methods provided in this application are described in detail below.

After collecting the EEG data, the terminal device can calculate the degree of correlation between the second EEG data of each two channels in the multiple channels to determine the brain connectivity image.

Specifically, since this application only needs to consider whether there is a correlation between two channels and does not need to consider whether the correlation is positive or negative, the terminal device can calculate the second EEG data of each two channels in the multiple channels. The absolute value of the correlation degree between each channel is then normalized to obtain the pixel value of the pixel point at the corresponding position to connect the pixels at each position in the image according to the brain. Pixel values of points to generate brain connectivity images.

Figures 3 and 4 respectively show the brain connectivity maps of autistic patients and normal people. It can be seen from the figures that there are certain differences in the brain connectivity maps of autistic patients and normal people. Therefore, it can be determined whether the brain connectivity image of the subject to be evaluated is closer to the brain connectivity map of autistic patients or to the brain connectivity map of normal people to complete the autism assessment.

Specifically, the terminal device can input the brain connectivity map into the autism classification model. The autism classification model can be a convolutional neural network model, a fully connected neural network model, or a neural network model with other structures. This model can extract features from brain connected images and can be trained through a large number of sample images. The training methods include: Not limited to gradient descent, momentum, or other optimization methods.

In some implementations, as shown in Figure 5, the autism classification model may include 5 convolutional layers, 5 max pooling layers, and 3 fully connected layers. Since the constructed brain connectivity map is a grayscale image obtained after normalization, assuming that the total number of channels is 125, the size of the data input to the autism classification model is 125×125×1. After the first convolution layer and pooling After the convolution layer, the data size can be changed to 62×62×64, and then after passing through 4 layers of convolution layers and pooling layers, the data size can be changed to 3×3×256, and then through three fully connected layers, and finally connected The classifier obtains the final binary classification result. The binary classification result is also the autism assessment result.

In practical applications, the second EEG data of each channel includes third EEG data of multiple frequency bands. That is to say, the second EEG data of one channel may include a plurality of third EEG data divided according to different frequency bands. The frequency band here may specifically include multiple sub-frequency bands within the full frequency band, or include the full frequency band and one or more sub-frequency bands within the full frequency band. Among them, the full frequency band can refer to the frequency band covered by metadata, which is the EEG data directly collected through the electrode pads or the data obtained after preprocessing the EEG data directly collected by the electrode pads. The terminal device can use the filter to perform frequency division processing on the metadata to obtain the third EEG data of multiple sub-bands, which is composed of the third EEG data of multiple sub-bands and the third EEG data of the full frequency band (i.e., metadata). Second EEG data. Specifically, the above sub-bands and corresponding frequency ranges can be respectively: delta wave (0.5-4 Hz), theta wave (4-8 Hz), alpha wave (8-13 Hz), beta wave (13-30 Hz) , γ wave (30-50 Hz).

Correspondingly, the terminal device can determine the correlation degree of the third EEG data in the same frequency band between every two channels in the plurality of channels, and obtain the third EEG data in each frequency band between every two channels in the plurality of channels. The degree of correlation of the data is used to determine the pixel values of the pixels at each position in the brain connectivity image of the corresponding frequency band, and the brain connectivity image of each frequency band is obtained. For the determination process of the brain connectivity image of each frequency band, please refer to the description of step S102, which will not be described in detail in this application.

Based on the brain connectivity image of each frequency band, the terminal device can determine the preliminary assessment results corresponding to each frequency band, and based on the preliminary assessment results corresponding to each frequency band, determine the autism assessment result of the subject to be evaluated.

Taking the aforementioned five sub-bands as an example, the terminal device can determine the brain connectivity images corresponding to the five sub-bands and the brain connectivity image corresponding to the full frequency band, for a total of six brain connectivity images. A preliminary assessment result can be determined based on each brain connectivity image, and then the 6 preliminary assessment results are fused to obtain the autism assessment result of the subject to be assessed.

For example, if there are N or more preliminary assessment results indicating high risk for autism, the autism assessment result can be determined to be high risk for autism; otherwise, the autism assessment result can be determined to be high risk for autism. Low risk. Among them, N is a positive integer greater than or equal to 1 and less than or equal to the number of frequency bands. The specific value can be adjusted according to the actual situation, for example, it can be 2.

For another example, a preliminary evaluation result can be determined based on each brain connectivity image. The preliminary evaluation result is a confidence level that the risk of autism is high. Weighted fusion of each confidence level can obtain a fused confidence level. If the fusion If the final confidence level is higher than the preset confidence threshold, the autism assessment result can be determined to be at high autism risk; otherwise, the autism assessment result can be determined to be at low autism risk.

More specifically, the terminal device can use sample data in different frequency bands to train autism classification models in different frequency bands, and then input the brain connectivity image to the autism classification model in the corresponding frequency band to obtain preliminary evaluation results in the corresponding frequency band. In this way, the model corresponds one-to-one with the frequency bands of the EEG data, which can ensure the reliability of the preliminary assessment results and thus the accuracy of the autism assessment results.

Use the method provided by this application to train autism classification models in each frequency band and test autistic patients and normal people. After experiments, the recognition accuracy of the autism classification model in each frequency band is as shown in the table below, where, using The β-wave autism classification model has the highest recognition accuracy, reaching 99.01%.

Based on the above experimental results, the terminal device can also determine the degree of correlation of the fourth EEG data between each two channels in the multiple channels to determine the pixel values of the pixels at each position in the brain connectivity image of the target frequency band, and obtain Image of brain connectivity in target frequency bands. Then, autism assessment results are determined based on the brain connectivity image of the target frequency band. The fourth EEG data is the EEG data in the target frequency band.

The target frequency band may be a preset frequency band, for example, it may refer to the frequency band with the highest accuracy in autism assessment results verified by experiments, such as the aforementioned beta wave.

Specifically, the terminal device can input the brain connectivity image of the target band to the autism classification model of the target band, and use the preliminary evaluation result output as the autism evaluation result. Among them, the autism classification model in the target frequency band is a model trained based on sample images, and the sample images are sample brain connectivity images determined based on sample EEG data in the target frequency band.

To sum up, this application analyzes the differences between autistic patients and normal people from the perspective of brain functional connectivity, uses EEG data to construct a brain connectivity map that represents brain functional connectivity, and inputs it into the neural network model to The risk level of autism of the subject to be assessed has a certain degree of physiological interpretability. Using the brain connectivity map as a reference, the risk of autism of the subject to be assessed can be accurately assessed. The above experimental results also confirm that the method provided by this application has high reliability.

It should be noted that for the sake of simple description, the foregoing method embodiments are expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence. Because according to this application, certain steps can be performed in other orders.

Figure 6 shows a schematic structural diagram of an autism assessment device 600 based on EEG data provided by an embodiment of the present application. The autism assessment device 600 based on EEG data is configured on a terminal device.

Specifically, the autism assessment device 600 based on EEG data may include:

The acquisition unit 601 is used to acquire the first EEG data of the whole brain area of the subject to be evaluated, where the first EEG data includes multiple channels of second EEG data;

Determining unit 602, configured to determine a brain connectivity image based on the first EEG data, where the brain connectivity image is used to characterize the degree of correlation between the second EEG data of each two channels in the plurality of channels. ;

The evaluation unit 603 is configured to determine the autism evaluation result of the subject to be evaluated based on the brain connectivity image.

In some embodiments of the present application, the above-mentioned acquisition unit 601 may be specifically configured to: acquire the second EEG data collected by the electrode sheets corresponding to each of the plurality of channels. Each of the electrode sheets Arranged non-overlappingly outside the cerebral cortex of the subject to be evaluated.

In some embodiments of the present application, the above-mentioned determining unit 602 may be specifically configured to: determine the degree of correlation between the second EEG data of each two channels in the plurality of channels; determine based on the degree of correlation, The pixel values of the pixel points at each position in the brain connectivity image are used to obtain the brain connectivity image.

In some embodiments of the present application, the above-mentioned determining unit 602 may be specifically configured to: calculate the absolute value of the degree of correlation between the second EEG data of each two channels in the plurality of channels; The absolute value of the correlation degree between each two channels in each channel is normalized to obtain the pixel value of the pixel point at the corresponding position; based on the pixel value of the pixel point at each position in the brain connectivity image, the brain connectivity is generated image.

In some embodiments of the present application, the second EEG data of each channel in the plurality of channels includes third EEG data of multiple frequency bands; accordingly, the determination unit 602 may be specifically configured to: determine the plurality of EEG data. The correlation degree of the third brain electrical data in the same frequency band between every two channels in the channels is obtained to obtain the third brain electrical data in each frequency band between every two channels in the plurality of channels. The degree of correlation of the electrical data; according to the degree of correlation of the third EEG data in each of the frequency bands between every two channels in the plurality of channels, determine each position in the brain connectivity image of the corresponding frequency band. The pixel values of the pixels are used to obtain the brain connectivity image of each frequency band; the evaluation unit 603 may be further specifically configured to: determine the brain connectivity image corresponding to each frequency band based on the brain connectivity image of each frequency band. Preliminary assessment results; determine the autism assessment result of the subject to be assessed based on the preliminary assessment results corresponding to each frequency band.

In some embodiments of the present application, the second EEG data of each channel in the plurality of channels is the fourth EEG data of the target frequency band.

In some embodiments of the present application, the evaluation unit 603 may be specifically configured to: input the brain connectivity image of the target frequency band into the autism classification model, and obtain the self-image output by the autism classification model. Autism assessment results, wherein the autism classification model is a model trained based on sample images, and the sample images are sample brain connectivity images determined based on sample EEG data in the target frequency band.

It should be noted that, for the convenience and simplicity of description, for the specific working process of the above-mentioned autism assessment device 600 based on EEG data, reference can be made to the corresponding processes of the methods described in Figures 1 to 5, and will not be described again here.

As shown in Figure 7, it is a schematic diagram of a terminal device provided by an embodiment of the present application. The terminal device 7 may include: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70, such as an autism assessment program. When the processor 70 executes the computer program 72, it implements the steps in each of the above autism assessment method embodiments, such as steps S101 to S103 shown in Figure 1. Alternatively, when the processor 70 executes the computer program 72, it implements the functions of each module/unit in each of the above device embodiments, such as the acquisition unit 601, the determination unit 602 and the evaluation unit 603 shown in FIG. 6 .

The computer program may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 71 and executed by the processor 70 to complete the present application. The one or more modules/units may be a series of computer program instruction segments capable of completing specific functions. The instruction segments are used to describe the execution process of the computer program in the terminal device.

For example, the computer program can be divided into: an acquisition unit, a determination unit and an evaluation unit.

The specific functions of each unit are as follows: an acquisition unit, used to obtain the first EEG data of the entire brain area of the subject to be evaluated, where the first EEG data includes second EEG data of multiple channels; a determination unit, used according to The first EEG data determines a brain connectivity image, and the brain connectivity image is used to characterize the degree of correlation between the second EEG data of each two channels in the plurality of channels; the evaluation unit is configured to The brain connection image determines the autism assessment result of the subject to be assessed.

The terminal device may include, but is not limited to, a processor 70 and a memory 71 . Those skilled in the art can understand that Figure 7 is only an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as The terminal device may also include input and output devices, network access devices, buses, etc.

The so-called processor 70 can be a central processing unit (Central Processing Unit, CPU), or other general-purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit (ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

The memory 71 may be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. The memory 71 may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), or a secure digital (Secure Digital, SD) card equipped on the terminal device. Flash Card, etc. Further, the memory 71 may also include both an internal storage unit of the terminal device and an external storage device. The memory 71 is used to store the computer program and other programs and data required by the terminal device. The memory 71 can also be used to temporarily store data that has been output or is to be output.

It should be noted that, for the convenience and simplicity of description, the structure of the above terminal device may also refer to the specific description of the structure in the method embodiment, and will not be described again here.

Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above functional units and modules is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs. Module completion means dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be hardware-based. It can also be implemented in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present application. For the specific working processes of the units and modules in the above system, please refer to the corresponding processes in the foregoing method embodiments, and will not be described again here.

In the above embodiments, each embodiment is described with its own emphasis. For parts that are not detailed or documented in a certain embodiment, please refer to the relevant descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Experts and technicians may use different methods to implement the described functions for each specific application, but such implementations should not be considered to be beyond the scope of this application.

In the embodiments provided in this application, it should be understood that the disclosed apparatus/terminal equipment and methods can be implemented in other ways. For example, the device/terminal equipment embodiments described above are only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units. Or components can be combined or can be integrated into another system, or some features can be omitted, or not implemented. On the other hand, the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or units, which may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in various embodiments of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated units can be implemented in the form of hardware or software functional units.

If the integrated module/unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the processes in the methods of the above embodiments, which can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer can When the program is executed by the processor, the steps of each of the above method embodiments can be implemented. Wherein, the computer program includes computer program code, which may be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (Read-Only Memory, ROM) , random access memory (Random Access Memory, RAM), electrical carrier signals, telecommunications signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately added or deleted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium Excludes electrical carrier signals and telecommunications signals.

The above-described embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still implement the above-mentioned implementations. The technical solutions described in the examples are modified, or some of the technical features are equivalently replaced; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions in the embodiments of this application, and should be included in within the protection scope of this application.

Claims

An autism assessment device based on EEG data, characterized by including:

An acquisition unit, configured to acquire first EEG data of the entire brain area of the subject to be evaluated, where the first EEG data includes multiple channels of second EEG data;

a determination unit configured to determine a brain connectivity image based on the first EEG data, the brain connectivity image being used to characterize the degree of correlation between the second EEG data of each two channels in the plurality of channels;

An evaluation unit is configured to determine the autism evaluation result of the subject to be evaluated based on the brain connectivity image.
The autism assessment device based on EEG data according to claim 1, wherein said obtaining the first EEG data of the whole brain area of the subject to be evaluated includes:

The second EEG data collected by the electrode pieces corresponding to each of the plurality of channels is obtained, and each of the electrode pieces is arranged non-overlappingly outside the cerebral cortex of the subject to be evaluated.
The autism assessment device based on EEG data according to claim 1 or 2, wherein determining the brain connectivity image based on the first EEG data includes:

Determine the degree of correlation between the second EEG data of each two channels in the plurality of channels;

According to the degree of correlation, the pixel values of the pixel points at each position in the brain connectivity image are determined to obtain the brain connectivity image.
The autism assessment device based on EEG data according to claim 3, characterized in that, according to the degree of correlation, the pixel values of pixels at each position in the brain connectivity image are determined to obtain the Brain connectivity images, including:

Calculate the absolute value of the degree of correlation between the second EEG data of each two channels in the plurality of channels;

Normalize the absolute value of the correlation degree between each two channels in the plurality of channels to obtain the pixel value of the pixel point at the corresponding position;

The brain connectivity image is generated based on the pixel values of the pixel points at each position in the brain connectivity image.
The autism assessment device based on EEG data according to claim 3, wherein the second EEG data of each channel in the plurality of channels includes third EEG data of a plurality of frequency bands;

Determining the degree of correlation between the second EEG data of each two channels in the plurality of channels includes:

Determine the correlation degree of the third EEG data in the same frequency band between every two channels in the plurality of channels, and obtain the correlation degree of the third EEG data in the frequency band between every two channels in the plurality of channels. The degree of correlation of the third EEG data;

Determining the pixel values of pixels at each position in the brain connectivity image according to the degree of correlation to obtain the brain connectivity image includes:

According to the degree of correlation between each two channels of the plurality of channels in the third EEG data of each frequency band, determine the pixel value of the pixel point at each position in the brain connectivity image of the corresponding frequency band. , obtain the brain connectivity image of each frequency band;

Determining the autism assessment result of the subject to be assessed based on the brain connectivity image includes:

Determine the preliminary evaluation results corresponding to each frequency band based on the brain connectivity image of each frequency band;

According to the preliminary assessment results corresponding to each frequency band, the autism assessment result of the subject to be assessed is determined.
The autism assessment device based on EEG data according to claim 3, wherein the second EEG data of each channel in the plurality of channels is the fourth EEG data of the target frequency band.
The autism assessment device based on EEG data according to claim 6, wherein determining the autism assessment result based on the brain connectivity image of the target frequency band includes:

Input the brain connectivity image of the target frequency band into the autism classification model to obtain the autism assessment result output by the autism classification model, wherein the autism classification model is based on samples A model obtained through image training, where the sample image is a sample brain connectivity image determined based on sample EEG data of the target frequency band.
An autism assessment method based on EEG data, which is characterized by including:

Obtaining first EEG data of the entire brain area of the subject to be evaluated, where the first EEG data includes multiple channels of second EEG data;

Determine a brain connectivity image based on the first EEG data, the brain connectivity image being used to characterize the degree of correlation between the second EEG data of each two channels in the plurality of channels;

According to the brain connectivity image, the autism assessment result of the subject to be assessed is determined.
A terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that when the processor executes the computer program, it implements claims 1 to 1 Functions of the autism assessment device based on EEG data according to any one of 7.
A computer-readable storage medium, the computer-readable storage medium stores a computer program, characterized in that when the computer program is executed by a processor, the EEG data-based method as described in any one of claims 1 to 7 is implemented. Functionality of the autism assessment device.