Methods for detecting human brain age and intelligent system for predicting mathematical ability

Abstract

A method for detecting human brain age includes: a subject performing a task, scanning the subject's brain using an MRI scanner; outputting image data after the subject completes the task; a frontoparietal brain network data conversion module (FPN) converting the image data into frontoparietal brain network data; a salience brain network data conversion module (SN) converting the image data into salience brain network data; an artificial intelligence processing unit analyzing, verifying, and processing the frontoparietal brain network data and the salience brain network data and transmitting the data to a cloud database for comparison; and an intelligent learning module transmitting the detection result data to a data output unit, which outputs a detection report.

Description

Technical Field

[0001] This invention relates to a method for detecting human brain age and an intelligent system for predicting mathematical abilities. In particular, it provides a method for detecting human brain age and then using the intelligent system for computational analysis to achieve the effect of predicting mathematical abilities. Prior Technology

[0002] Due to advancements in science and technology, experts and scholars utilize various medical instruments to examine the human brain. Magnetic resonance imaging (MRI) scans can reveal the internal structure of the brain. During the process of creating brain structure maps, the subject typically lies relaxed while the MRI scan is performed. Therefore, through the efforts of many researchers, brain structures for different age groups have been established. Human cognitive development and brain function throughout the life cycle from childhood to adulthood are crucial processes. To identify brain dysfunction and atypical developments early, numerous studies have begun attempting to depict changes in cognition and brain function throughout the entire life cycle.

[0003] However, in the human cognitive system, non-symbolic quantitative abilities are the most fundamental abilities for mathematical learning and achievement, and have a significant impact on an individual's future mathematical learning outcomes.

[0004] In view of this, the inventor, through careful experimentation and research, and with a persistent spirit, has finally conceived an intelligent system for detecting human brain age and predicting mathematical abilities. After detecting the human brain, the intelligent system performs calculations and analyses to achieve the effect of predicting mathematical abilities.

[0005] The content disclosed in the above background description paragraph is only intended to enhance the understanding of the background technology of the present invention. Therefore, the above content contains prior art that does not constitute an obstacle to the present invention and should be well known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to propose a method for detecting human brain age and an intelligent system for predicting mathematical abilities. This system provides a method for detecting human brain age and then using intelligent system calculations and analysis to predict mathematical abilities.

[0007] To achieve the above objectives, this invention proposes a method for detecting human brain age, comprising: a subject performing a work task, using a magnetic resonance imaging (MRI) scanner to scan the subject's brain; after the subject completes the work task, the MRI scanner outputs image data and stores it in an image database; a data input unit transmits the image data from the image database to a frontoparietal network (FPN) data conversion module to convert the image data into frontoparietal network data; the data input unit transmits the image data from the image database to a salience network data conversion module. The frontoparietal network (SN) converts image data into salient brain network data; an artificial intelligence processing unit connects the frontoparietal network data conversion module (FPN) and the salient brain network data conversion module (SN) via signals. The artificial intelligence processing unit analyzes, verifies, and processes the frontoparietal network data and the salient brain network data and transmits the data to a cloud database for comparison; and an intelligent learning module transmits the detection result data to a data output unit, which outputs a detection report.

[0008] As described above, the method for detecting human brain age involves using an MRI scanner to output dynamic imaging data of brain function.

[0009] The method for detecting human brain age described above is used in subjects aged 7 to 30 years.

[0010] Following the aforementioned method for detecting human brain age, this task involves 64 attempts. During each attempt, the screen displays two sets of dot arrays simultaneously for 1 second, with the interval between attempts randomly ranging from 2 to 5 seconds. The subject performs this task while undergoing an MRI scan. After seeing the two sets of dot arrays, the subject quickly selects the set with the larger number of dots and presses the corresponding button (left or right). This task takes 6 to 7 minutes.

[0011] The method for detecting human brain age described above further includes: a high-resolution magnetic resonance imaging (MRI) instrument performing a high-resolution structural scan of the subject's brain; the subject lying flat on the MRI instrument and then remaining still for about 8 minutes; and the image data output by the MRI instrument being stored in the image database for image alignment.

[0012] As described above, the method for detecting human brain age involves preprocessing the image data output by the magnetic resonance imaging scanner by sequentially performing steps such as time correction, spatial correction, image alignment, and standardization.

[0013] As described above, the method for detecting human brain age involves the frontoparietal brain network data conversion module (FPN) and the salience brain network data conversion module (SN) capturing brain activity signals of the subject during the performance of the task to perform functional connectivity analysis between regions, ultimately obtaining a functional connectivity matrix, which is then used by an intelligent learning module to predict the subject's brain age.

[0014] Another objective of this invention is to propose an intelligent system for predicting mathematical abilities, which can provide the subject with a predicted brain age through an intelligent learning module, and the subject's age is between 7 and 30 years old, thereby achieving the purpose of predicting mathematical abilities.

[0015] To achieve the above objectives, this invention proposes an intelligent system for predicting mathematical abilities, comprising: a magnetic resonance imaging (MRI) scanner for scanning and detecting the brain of a subject and generating image data; an image database for storing the image data output by the MRI scanner; a data input unit for signal connection to the image database; and an intelligent learning module comprising: a data conversion module and an artificial intelligence processing unit, wherein the data conversion module is composed of a frontoparietal network data conversion module (FPN) and a salience network data conversion module (SN), and the frontoparietal network data conversion module (FPN) is signal-connected to the data input unit and the artificial intelligence processing unit. The system includes a frontoparietal network data conversion module (FPN) connected to the data input unit and the artificial intelligence processing unit; a cloud database containing numerous brain structure image data, which is connected to the artificial intelligence processing unit; and a data output unit connected to the artificial intelligence processing unit. When the data input unit receives image data from the image database, it undergoes data conversion via the frontoparietal network data conversion module (FPN) and the salience network data conversion module (SN). The data is then analyzed and verified by the artificial intelligence processing unit, and the output detection result data is transmitted to the data output unit.

[0016] Following the aforementioned intelligent system for predicting mathematical abilities, the Frontoparietal Network Data Transformation Module (FPN) provides data on functional connections in the frontoparietal network and processes non-symbolic quantitative judgments. The data provided by the FPN is synchronized data from the parietal network, which is an important feature for brain age prediction and cognitive function. When the FPN signal is input to the artificial intelligence processing unit, it is used to perform brain age prediction.

[0017] Following the aforementioned intelligent system for predicting mathematical abilities, the salient brain network data conversion module (SN) provides data on functional connections in the salient brain network and is responsible for identifying, processing important stimuli, and making quantitative judgments. The data provided by the salient brain network data conversion module (SN) is synchronized data of the salient brain network, which is an important feature for brain age prediction and cognitive function. When the signal of the salient brain network data conversion module (SN) is input to the artificial intelligence computing processor, it provides brain age prediction.

[0018] The intelligent system for predicting mathematical abilities, as described above, further includes a five-fold hierarchical cross-validation module within its artificial intelligence processing unit. This module provides a more stable and reliable training and validation process for the intelligent learning module. The five-fold hierarchical cross-validation module divides the data into five parts, each maintaining the same proportion based on age characteristics, thus avoiding data imbalance during training and ensuring better predictive performance when new data is provided.

[0019] This "Summary of the Invention" introduces some selected concepts in a simplified form. The "Implementation Methods" section below will provide a more detailed explanation with corresponding drawings. This "Summary of the Invention" is not intended to identify key or essential features of the subject matter of the patent application, nor is it intended to limit the scope of the subject matter of the patent application. Simple Explanation of the Diagram

[0020] The invention will be more fully understood through the detailed description and accompanying drawings, which illustrate the embodiments of the invention. Therefore, the following drawings are only for explaining the embodiments of the invention and do not limit the scope of the claims. Figure 1 is a block diagram of the first embodiment of the present invention. Figure 2 is a block diagram of the second embodiment of the present invention. Figure 3 is a schematic diagram of the brain age detection process of the present invention. Figure 4 is a schematic diagram of another embodiment of the brain age detection process of the present invention. Figure 5 is a schematic diagram of the computational processing of the five-fold layered cross-validation module of the present invention. Figure 6 is a schematic diagram of the detection result data of the present invention. Figure 7 is a schematic diagram of the 16 brain regions of the frontoparietal brain network (FPN) of this invention. Figure 8 is a schematic diagram of the eight brain regions of the salient brain network (SN) of this invention. Figure 9 is a schematic diagram of the frontoparietal brain network (FPN) and salient brain network (SN) of the present invention, comprising a total of 24 brain regions. Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0022] The advantages and features of the present invention, as well as the methods of achieving them, will be more readily understood by referring to exemplary embodiments and accompanying drawings. However, the invention may be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments provided will, to those skilled in the art, make this disclosure more thorough, complete, and fully convey the scope of the invention, which will be defined only as defined in the appended claims. In the figures, the dimensions and relative dimensions of elements are shown in an exaggerated manner for clarity. Throughout this specification, certain different element symbols may refer to the same element. As used herein, the terms "and / or" include any and all combinations of one or more of the associated listed objects.

[0023] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It will be further understood that terms defined, for example, in commonly used dictionaries, shall be understood to have the same meaning as those in the relevant field, and unless explicitly defined herein, shall be understood in the general sense as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0024] The following detailed description of illustrative embodiments, accompanied by accompanying drawings, is provided. However, these embodiments may be included in different forms and should not be construed as limiting the scope of the invention. These embodiments are provided to make the disclosure of the invention complete and clear, and those skilled in the art will be able to understand the scope of the invention through these embodiments.

[0025] The following content will further clarify and fully explain the specific technical solution of this utility model in conjunction with specific embodiments.

[0026] Please refer to Figure 1, which is a block diagram of the first embodiment of the present invention. The intelligent system for predicting mathematical abilities of the present invention includes: a magnetic resonance imaging (MRI) scanner 10, which provides scanning and detection of the brain of a subject and generates image data; an image database 20, which stores the image data output by the MRI scanner 10; a data input unit 30, which is signal-connected to the image database 20; and an intelligent learning module 40, which includes: a data conversion module 45 and an artificial intelligence processing unit 43. The data conversion module 45 is composed of a frontoparietal brain network data conversion module (FPN) 41 and a salience brain network data conversion module (SN) 42. The frontoparietal brain network data conversion module (FPN) 41 is signal-connected to the data input unit 30 and the image database 20. The system includes an artificial intelligence processing unit 43; a salience brain network data conversion module (SN) 42 connected to the data input unit 30 and the artificial intelligence processing unit 43; a cloud database 50 providing storage of numerous brain structure image data, which is connected to the artificial intelligence processing unit 43; and a data output unit 60 connected to the artificial intelligence processing unit 43. When the data input unit 30 inputs image data from the image database, it undergoes data conversion via the frontoparietal brain network data conversion module (FPN) 41 and the salience brain network data conversion module (SN) 42. The data is then analyzed and verified by the artificial intelligence processing unit 43, and the output detection result data is transmitted to the data output unit 60.

[0027] The frontoparietal brain network data conversion module (FPN) 41 of the present invention provides data on the functional connectivity of the frontoparietal brain network and processes non-symbolic quantitative judgments. The data provided by the frontoparietal brain network data conversion module (FPN) 41 is synchronized data of the frontoparietal brain network, which is an important feature for brain age prediction and cognitive function. When the signal of the frontoparietal brain network data conversion module (FPN) 41 is input to the artificial intelligence computing processor 43, it provides brain age prediction.

[0028] In the salient brain network data conversion module (SN) 42 of the present invention, it provides data on the functional connections in the salient brain network and is responsible for identifying, processing important stimuli and processing quantity judgments. The data provided by the salient brain network data conversion module (SN) 42 is the synchronization data of the salient brain network, which is an important feature for brain age prediction and cognitive function. When the signal of the salient brain network data conversion module (SN) 42 is input to the artificial intelligence computing processor 43, it is used to perform brain age prediction.

[0029] Please refer to Figure 2, which is a block diagram of the second embodiment of the present invention. To provide a more stable and reliable training and verification process for the intelligent learning module, in the second embodiment, the intelligent system for predicting mathematical abilities of the present invention includes: a magnetic resonance imaging (MRI) scanner 10, which scans and detects the brain of a subject and generates image data; an image database 20, which stores the image data output by the MRI scanner 10; a data input unit 30, which is signal-connected to the image database 20; and an intelligent learning module 40, which includes: a frontoparietal brain network data conversion module (FPN) 41, a salience brain network data conversion module (SN) 42, and an artificial intelligence processing unit 43. The frontoparietal brain network data conversion module (FPN) 41 is signal-connected to the data input unit 30 and the artificial intelligence processing unit 43; the salience brain network data conversion module (SN) 42 is signal-connected to the data input unit 30 and the artificial intelligence processing unit 43, wherein the artificial intelligence processing unit... The processor 43 further includes: a five-fold hierarchical cross-validation module 44, which provides a more stable and reliable training and validation process for the intelligent learning module 40. The five-fold hierarchical cross-validation module 44 divides the data into five parts, each of which maintains the same proportion according to age characteristics to avoid data imbalance during training and ensure better predictive performance when new data is provided; a cloud database 50, which provides and stores a large number of brain structure image data, and the cloud database 50 is signal-connected to the artificial intelligence computing processor 43; and a data output unit 60, which is signal-connected to the artificial intelligence computing processor 43. When the data input unit 30 inputs the image data from the image database 20, it will be processed by the frontoparietal brain network data conversion module (FPN) 41 and the salience brain network data conversion module (SN) 42 for data conversion. The data is then analyzed and validated by the artificial intelligence computing processor 43, and the output detection result data is transmitted to the data output unit 60.

[0030] Please refer to Figure 3, and also refer to Figures 1 and 2. Figure 3 is a schematic diagram of the brain age detection process of the present invention. When the method for detecting human brain age of the present invention is implemented, it includes the following steps:

[0031] Step 101: When a test subject is performing a work task, a magnetic resonance imaging (MRI) scanner 10 will be used to scan the test subject's brain;

[0032] Step 2 102: After the subject completes the task, the magnetic resonance imaging scanner 10 will output an image and store it in an image database 20;

[0033] Step 3 103: A data input unit 30 transmits the image data from the image database 20 to a frontoparietal brain network data conversion module (FPN) 41 to convert the image data into frontoparietal brain network data; the data input unit 30 also transmits the image data from the image database 20 to a salience brain network data conversion module (SN) 42 to convert the image data into salience brain network data.

[0034] Step 4 104: An artificial intelligence processing processor 43 connects to the frontoparietal brain network data conversion module (FPN) 41 and the salience brain network data conversion module (SN) 42. The artificial intelligence processing processor 43 analyzes, verifies, and processes the frontoparietal brain network data and the salience brain network data, and transmits the data to a cloud database 50 for comparison.

[0035] Step 5 105: An intelligent learning module 40 transmits the detection result data to a data output unit 60, which outputs a detection report 61.

[0036] The present invention provides a method for detecting human brain age, wherein the age of the subject is selected from 7 to 30 years old, and in step two 102, the image data output by the magnetic resonance imaging scanner is a dynamic image data of brain function.

[0037] In step 101, the task performed by the test subject consists of 64 attempts. During each attempt, the screen displays two sets of dot arrays simultaneously for 1 second, and the interval between each attempt is randomly between 2 and 5 seconds. The test subject performs the task while being scanned by the MRI scanner. After seeing the two sets of dot arrays, the test subject quickly selects the set with the larger number of dots and presses the corresponding button (left or right). The task takes 6 to 7 minutes.

[0038] To make the data for predicting brain age more accurate, the present invention adds a high-resolution magnetic resonance imaging (MRI) scanning step 200 between step two 102 and step three 103 in the method for detecting human brain age, as shown in Figure 4, and also in conjunction with Figures 1 and 2. Figure 4 is a schematic diagram of another embodiment of the brain age detection process of the present invention. When the method for detecting human brain age of the present invention is further implemented, it includes the following steps:

[0039] Step 101: When a test subject is performing a work task, a magnetic resonance imaging (MRI) scanner 10 will be used to scan the test subject's brain;

[0040] Step 2 102: After the subject completes the task, the magnetic resonance imaging scanner 10 will output an image and store it in an image database 20;

[0041] High-resolution magnetic resonance imaging (MRI) scanning procedure 200: A high-resolution MRI scanner performs a high-resolution structural scan of the subject's brain. The subject lies supine on the high-resolution MRI scanner and then remains still for approximately 8 minutes. The image data output by the high-resolution MRI scanner is then stored in the image database 20 for image alignment purposes.

[0042] Step 3 103: A data input unit 30 transmits the image data from the image database 20 to a frontoparietal brain network data conversion module (FPN) 41 to convert the image data into frontoparietal brain network data; the data input unit 30 also transmits the image data from the image database 20 to a salience brain network data conversion module (SN) 42 to convert the image data into salience brain network data.

[0043] Step 4 104: An artificial intelligence processing processor 43 connects to the frontoparietal brain network data conversion module (FPN) 41 and the salience brain network data conversion module (SN) 42. The artificial intelligence processing processor 43 analyzes, verifies, and processes the frontoparietal brain network data and the salience brain network data, and transmits the data to a cloud database 50 for comparison.

[0044] Step 5 105: An intelligent learning module 40 transmits the detection result data to a data output unit 60, which outputs a detection report 61.

[0045] Before performing step 3 103, the method for detecting human brain age in this invention preprocesses the data. The image data output by the magnetic resonance imaging scanner 10 undergoes time correction, spatial correction, image alignment and standardization in sequence to preprocess the data.

[0046] Therefore, the frontoparietal brain network data conversion module (FPN) 41 and the salience brain network data conversion module (SN) 42 extract the brain activity signals of the test subject during the performance of the task to perform functional connectivity analysis between regions, and finally obtain the functional connectivity matrix. Then, through the intelligent learning module 40, the brain age of the test subject can be predicted.

[0047] The present invention relates to a method for detecting human brain age and an intelligent system for predicting mathematical abilities. In a further implementation, a five-fold hierarchical cross-validation module 44 is set within the artificial intelligence processing unit 43. Please refer to Figure 5, which is a schematic diagram of the five-fold hierarchical cross-validation module of the present invention performing computational processing. Also refer to Figure 2. The five-fold hierarchical cross-validation module 44 provides a more stable and reliable training and validation process for the intelligent learning module 40. The five-fold hierarchical cross-validation module 44 divides the data into five parts, each of which maintains the same proportion according to age characteristics, avoiding data imbalance during the training process and ensuring better predictive performance when new data is provided.

[0048] Please refer to Figure 6, which is a schematic diagram of the data of the detection results of the present invention. Also refer to Figures 1 and 2. The present invention uses the intelligent learning module 40 to provide a prediction of the brain age of the test subject and uses the data output unit 60 to generate a detection report 61. The data of the predicted brain age can be obtained from the detection report 61, and the data of the predicted mathematical ability can be obtained through the calculation and processing of the artificial intelligence computing processor 43.

[0049] To enable those skilled in the art to better understand the function of the frontoparietal brain network data conversion module (FPN) 41 and the salience brain network data conversion module (SN) 42 of the present invention, the following detailed description is provided: The image data output by the magnetic resonance imaging scanner of the present invention is a dynamic image data of brain function. The so-called functional connectivity (FC) refers to the synchronous activity patterns between brain regions. Through this method, we can understand the collaborative relationship between various regions in a specific state or task process. The brain does not rely on a single region for operation, but rather processes different tasks through the interaction and cooperation of multiple brain regions.

[0050] In its implementation, this invention pays particular attention to the functional connections between the frontoparietal network (FPN) and the salience network (SN), as these two networks are especially important for the development of quantitative processing and mathematical abilities.

[0051] Please refer to Figures 7, 9 and 1. The Frontoparietal Network Data Conversion Module (FPN) 41 of the present invention provides data for retrieving functional connectivity data from the Frontoparietal Network (FPN) 411. The Frontoparietal Network Data Conversion Module (FPN) 411 is mainly responsible for higher-level cognitive processes such as executive function, working memory and mathematical calculation. When comparing quantities or performing mathematical operations, multiple brain regions in this network need to cooperate with each other to effectively process information.

[0052] This invention primarily utilizes the AAL3 (Automated Anatomical Labeling) brain atlas, selecting 24 brain regions belonging to the frontoparietal network (FPN) 411 and the salience network (SN) 421 (all regions include both sides). The frontoparietal network (FPN) 411 comprises 16 brain regions, as shown in Figures 7 and 9. The circular black dots in the figures indicate the 16 brain regions of the frontoparietal network (FPN) 411, which are: the frontal lobe (8 regions), one region each on the left and right sides of the middle frontal gyrus (MFG), and six regions in the inferior frontal gyrus (IFG). The frontal lobe (8 regions) includes: the superior parietal lobe (SPL): one region each on the left and right sides, the inferior parietal lobe (SPL), and... IPL: 1 brain region on each side; Angular Gyrus (AG): 1 brain region on each side; and Superior Gyrus (SMG): 1 brain region on each side.

[0053] The salient brain network (SN) 421 has eight brain regions. Please refer to Figures 8 and 9. The circular blocks in the figures indicate the eight brain regions of the salient brain network (SN) 421, which are: Insula (INS): one brain region on each side and Anterior Cingulate Cortex (ACC): three brain regions on each side.

[0054] The salience network data conversion module (SN) 42 of this invention provides data on the functional connections in the salience network (SN) 421. The salience network (SN) 421 is used to detect key information in the environment and allocate resources among multiple cognitive tasks. In the process of quantitative comparison, if it is necessary to focus on more distinctive information, the salience network (SN) 421 will be activated to help the brain determine which clues are worth investing more cognitive resources in. Therefore, the interaction between the frontoparietal network (FPN) 411 and the salience network (SN) 421 will affect the development of mathematical ability, and their functional connections will also change with age.

[0055] Therefore, the present invention's method for detecting human brain age, when extracting functional connectivity, uses functional magnetic resonance imaging (fMRI) to record the subject's brain activity during a quantitative comparison task, and calculates the functional connectivity between different brain regions using time-series analysis. Each brain region has a time-varying blood oxygen concentration signal (BOLD signal) representing the neural activity in that region. To assess the synchronicity between two brain regions, their Pearson correlation coefficient is calculated. If the correlation coefficient between two brain regions is positive, it indicates that their activity trends are similar and they may be cooperating in the same cognitive process; the closer the value is to +1, the higher their synchronicity. If the correlation coefficient is close to 0, it indicates that the functional connectivity between the two regions is weak, and they may not be participating in the same task processing simultaneously; when the correlation coefficient is negative, it indicates that the activity patterns of the two brain regions are opposite, and there may be a competitive or mutually inhibitory relationship; the closer to -1, the stronger this inverse relationship.

[0056] In this process, in addition to calculating the functional connectivity within the frontoparietal network (FPN) 411 and the salient network (SN) 421, the cross-network connectivity between the frontoparietal network (FPN) 411 and the salient network (SN) 421 is also evaluated. These functional connectivity indicators will be used together as the neural characteristics of the test subjects to depict the collaborative operation patterns between different brain regions during quantitative tasks and will be used for subsequent brain age prediction analysis.

[0057] While the present invention has been disclosed above with reference to the preferred embodiments, it is not intended to limit the invention. Those skilled in the art can make modifications and refinements without departing from the spirit and scope of the invention. Therefore, the scope of patent protection for this invention shall be determined by the claims outlined in the appended specification. However, the specific embodiments described above are merely illustrative of the features and effects of the invention and are not intended to limit the scope of its implementation. Any equivalent changes and modifications made using the content disclosed in this invention without departing from the spirit and technical scope of the invention as described above shall still be covered by the following claims.

[0058] 10: Magnetic Resonance Imaging Scanner 20: Image Database 30: Data Input Unit 40: Intelligent Learning Module 41: Frontoparietal Brain Network Data Transformation Module (FPN) 42: Significant Brain Network Data Transformation Module (SN) 43: Artificial Intelligence Processing Unit 44: Five-fold tiered cross-validation module 45: Data Conversion Module 50: Cloud-based database 60: Data Output Unit 61: Test Report 101: Step One 102: Step Two 103: Step Three 104: Step Four 105: Step Five 200: High-resolution magnetic resonance imaging (MRI) scanning procedure 411: Frontoparietal Network (FPN) 421: Significant Brain Networks (SN)

Claims

1. A method for detecting human brain age, comprising: When a subject performs a task, their brain is scanned using an MRI scanner. After the subject completes the task, the MRI scanner outputs image data and stores it in an image database. The image data output by the MRI scanner is dynamic image data of brain function. A data input unit transmits the image data from the image database to a frontoparietal brain network data conversion module (FPN) to convert the image data into frontoparietal brain network data. The data input unit then transmits the image data from the image database to a salience brain network data conversion module (SN) to convert the image data into salience brain network data. An artificial intelligence processing unit connects to the frontoparietal brain network data conversion module (FPN) and the salience brain network data conversion module (SN). The AI ​​processing unit analyzes and verifies the frontoparietal brain network data and the salience brain network data and transmits the data to a cloud database for comparison. An intelligent learning module transmits the detection result data to a data output unit, which outputs a detection report. The task involves 64 attempts. During each attempt, the screen displays two sets of dot arrays simultaneously for 1 second, with the interval between attempts randomly ranging from 2 to 5 seconds. The subject performs the task while being scanned by an MRI scanner. After seeing the two sets of dot arrays, the subject quickly selects the set with the larger number of dots and presses the corresponding button (left or right). The task takes 6 to 7 minutes.

2. The method for detecting human brain age as described in claim 1, wherein the subject is aged between 7 and 30 years old.

3. The method for detecting human brain age as described in claim 1 further includes: a high-resolution magnetic resonance imaging (MRI) instrument performing a high-resolution structural scan of the subject's brain, the subject lying flat on the MRI instrument and then remaining still for about 8 minutes, and the image data output by the MRI instrument being stored in the image database for image alignment purposes.

4. The method for detecting human brain age as described in claim 1, wherein the image data output by the magnetic resonance imaging scanner is subjected to time correction, spatial correction, image alignment and standardization processing in sequence for data preprocessing.

5. The method for detecting human brain age as described in claim 1, wherein the frontoparietal brain network data conversion module (FPN) and the salience brain network data conversion module (SN) are used to capture brain activity signals of the subject during the performance of the task, perform functional connectivity analysis between regions, and finally obtain a functional connectivity matrix, which is then used through an intelligent learning module to predict the brain age of the subject.

6. An intelligent system for predicting mathematical abilities, comprising: a magnetic resonance imaging (MRI) scanner for scanning and detecting the brain of a subject and generating image data; an image database for storing the image data output by the MRI scanner; a data input unit for signal connection to the image database; and an intelligent learning module comprising: a data conversion module and an artificial intelligence processing unit, wherein the data conversion module is composed of a frontoparietal network data conversion module (FPN) and a salience network data conversion module (SN), the frontoparietal network data conversion module (FPN) being signal-connected to the data input unit and the artificial intelligence processing unit; and the salience network data conversion module (SN) being signal-connected to the data input unit and the artificial intelligence processing unit. A cloud database provides storage for numerous brain structure image data, which is signal-connected to the artificial intelligence computing processor; and a data output unit is signal-connected to the artificial intelligence computing processor. When the data input unit inputs image data from the image database, it undergoes data conversion through the frontoparietal brain network data conversion module (FPN) and the salience brain network data conversion module (SN). The data is then analyzed and verified by the artificial intelligence computing processor, and the output detection result data is transmitted to the data output unit.

7. The intelligent system for predicting mathematical abilities as described in claim 6, wherein the frontoparietal brain network data conversion module (FPN) provides data for extracting functional connectivity data from the frontoparietal brain network and processing non-symbolic quantitative judgments, and the data provided by the frontoparietal brain network data conversion module (FPN) is synchronized data from the parietal brain network, which is an important feature for brain age prediction and cognitive function. When the frontoparietal brain network data conversion module (FPN) signal is input to the artificial intelligence computing processor, it provides brain age prediction.

8. The intelligent system for predicting mathematical abilities as described in claim 6, wherein the salient brain network data conversion module (SN) provides data for extracting functional connectivity data from the salient brain network and is responsible for identifying, processing important stimuli and processing quantity judgments. The data provided by the salient brain network data conversion module (SN) is synchronized data of the salient brain network, which is an important feature for brain age prediction and cognitive function. When the signal of the salient brain network data conversion module (SN) is input to the artificial intelligence computing processor, it provides brain age prediction.

9. The intelligent system for predicting mathematical abilities as described in claim 6, wherein the artificial intelligence computing processor further includes: a five-fold hierarchical cross-validation module, which provides a more stable and reliable training and validation process for the intelligent learning module, and the five-fold hierarchical cross-validation module divides the data into five parts, each part maintaining the same proportion according to age characteristics, avoiding data imbalance during the training process, so as to ensure better prediction results when new data is provided.

Images