A system and method for predicting cognitive decline in type 2 diabetes

Abstract

The present application belongs to the technical field of medical health, and specifically relates to a type 2 diabetes cognitive function decline prediction system and method. The present application can timely find the cognitive function decline trend by real-time monitoring and analyzing the cognitive function impairment of type 2 diabetes patients, thereby providing a scientific basis for clinical diagnosis and treatment. Through accurate image processing and data analysis, the present application can effectively predict the safety boundary of cognitive function decline and provide personalized prevention and intervention measures for patients. In addition, the present application can accurately assess the level of cognitive function decline according to the diffusion tensor of cognitive function impairment, thereby providing an important reference for doctors to develop treatment plans, and ultimately helping to improve the quality of life of type 2 diabetes patients and reduce the risk of cognitive impairment.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of medical health, and particularly relates to a type 2 diabetes cognitive impairment prediction system and method. BACKGROUND

[0002] With the aging of the population and the change of lifestyle, the incidence of type 2 diabetes is increasing year by year, and diabetes not only affects the blood glucose level of patients, but also can cause various complications, including cognitive impairment, which is one of the common neurological complications of diabetic patients, and it can seriously affect the quality of life of patients, so early prediction and intervention of cognitive impairment in type 2 diabetes patients are particularly important.

[0003] At present, although there have been studies on the relationship between diabetes and cognitive impairment, there is a lack of effective prediction models and systems to accurately assess and predict the progress of cognitive impairment, and the present application proposes a new type 2 diabetes cognitive impairment prediction system and method, which aims to predict the safety boundary of cognitive impairment by real-time monitoring and analyzing the diffusion tensor of the cognitive impairment area, and determine the level of cognitive impairment, so as to provide more accurate diagnosis and treatment basis for clinical. SUMMARY

[0004] The purpose of the present application is to provide a type 2 diabetes cognitive impairment prediction system and method, which can real-time monitor and analyze the diffusion tensor of the cognitive impairment area, predict the safety boundary of cognitive impairment, and determine the level of cognitive impairment, so as to improve the quality of life of type 2 diabetes patients.

[0005] The technical solutions adopted by the present application are as follows:

[0006] A type 2 diabetes cognitive impairment prediction method, comprising:

[0007] Pretreating the obtained brain region image data and outputting as base image data;

[0008] Extracting features from the base image data to obtain brain region feature images related to cognitive function;

[0009] Labeling cognitive impairment areas and non-impairment areas in the brain region feature area, and real-time monitoring the diffusion tensor of the cognitive impairment area;

[0010] Periodically analyzing the diffusion tensor of the cognitive impairment area, and synchronously outputting the cognitive impairment state, wherein the cognitive impairment state includes a suppression state and an abnormal state;

[0011] The inhibition state indicates that the diffusion tensor of the cognitive impairment area is within a normal range, and the diffusion tensor within the normal range is recorded as a first condition parameter, and a safe boundary of cognitive decline is predicted according to the first condition parameter;

[0012] The abnormal state indicates that the diffusion tensor of the cognitive impairment area is abnormal, and is output as a second condition parameter at the same time, and a cognitive decline level is determined according to the second condition parameter.

[0013] In a preferred embodiment, the step of preprocessing the acquired brain region image data and outputting the base image data comprises:

[0014] The brain region image data is collected and a time stamp is added to obtain sample images;

[0015] The sample images are denoised to enhance the contrast of the images;

[0016] The denoised sample images are standardized to unify the format of all the sample images, and are recorded as base image data at the same time.

[0017] In a preferred embodiment, the step of real-time monitoring the diffusion tensor of the cognitive impairment area comprises:

[0018] An edge curve of the cognitive impairment area is obtained;

[0019] A virtual coordinate system is constructed, and the coordinates of each edge corner point in the edge curve in the virtual coordinate system are calculated and recorded as a reference coordinate parameter;

[0020] The cognitive impairment area damage area is calculated according to the reference coordinate parameter;

[0021] A monitoring period is constructed, and a plurality of monitoring nodes are set in the monitoring period, and the cognitive impairment area damage area under each monitoring node is collected in real time;

[0022] The cognitive impairment areas under adjacent monitoring nodes are subtracted to obtain the diffusion tensor of the cognitive impairment area.

[0023] In a preferred embodiment, the step of calculating the cognitive impairment area damage area according to the reference coordinate parameter comprises:

[0024] The reference coordinate parameter of the cognitive impairment area is obtained;

[0025] A preset calculation function is obtained;

[0026] The reference coordinate parameter is input into the calculation function, and the output result of the calculation function is recorded as the cognitive impairment area damage area.

[0027] In a preferred embodiment, the step of periodically analyzing the diffusion tensor of the cognitive impairment area and synchronously outputting the cognitive decline state comprises:

[0028] During the monitoring period, a plurality of equally spaced parallel periods are set;

[0029] The diffusion tensor of the cognitive impairment area is counted for each parallel period, and recorded as a state evaluation parameter;

[0030] The state evaluation threshold is obtained, and the state evaluation threshold is compared with the state evaluation parameter;

[0031] When the state evaluation parameter is less than the state evaluation threshold, it indicates that the diffusion of the cognitive impairment area is inhibited, and the cognitive decline state is recorded as an inhibition state;

[0032] When the state evaluation threshold is greater than or equal to the state evaluation threshold, it indicates that the diffusion of the cognitive impairment area is not inhibited, and the cognitive decline state is recorded as an abnormal state.

[0033] In a preferred embodiment, the step of predicting the safety boundary of cognitive decline according to the first condition parameter comprises:

[0034] The first condition parameter is obtained, and the first condition parameter is arranged according to the occurrence sequence;

[0035] An evaluation function is obtained, and the first condition parameter is input into the evaluation function according to the arrangement order of the first condition parameter, and the output result of the evaluation function is recorded as a trend condition parameter;

[0036] The allowable decline area corresponding to the first condition parameter is obtained;

[0037] A prediction function is obtained, and the allowable decline area and the trend condition parameter are input into the prediction function, and the output result of the prediction function is recorded as a predicted safety interval;

[0038] According to the predicted safety interval, the last output node of the first condition parameter is offset processed to obtain the safety boundary of the first condition parameter predicting cognitive decline.

[0039] In a preferred embodiment, after the trend condition parameter is output, it is compared with a preset standard trend value, and when the trend condition parameter exceeds the standard trend value, the prediction of the safety boundary of cognitive decline is stopped, and the inhibition state is converted into an abnormal state, otherwise, the prediction of the safety boundary of cognitive decline is continued.

[0040] In a preferred solution, the step of determining the cognitive function decline level according to the second condition parameter comprises:

[0041] obtaining the second condition parameter;

[0042] obtaining a grading interval, wherein a plurality of grading intervals are provided, and each grading interval corresponds to a cognitive function decline level;

[0043] pairing the second condition parameter with the grading interval, and matching the corresponding cognitive function decline level.

[0044] The application further provides a type 2 diabetes cognitive function decline prediction system using the type 2 diabetes cognitive function decline prediction method, comprising:

[0045] an image processing module, which is used for pre-processing the obtained brain region image data and outputting as basal image data;

[0046] a feature extraction module, which is used for feature extraction on the basal image data, and obtains brain region feature image related to cognitive function;

[0047] a marking module, which is used for marking the cognitive function damage region and the non-damage region in the brain region feature region, and monitoring the diffusion tensor of the cognitive function damage region in real time;

[0048] a state evaluation module, which is used for phased analysis on the diffusion tensor of the cognitive function damage region, and synchronously outputs the cognitive function decline state, wherein the cognitive function decline state comprises a suppression state and an abnormal state;

[0049] a prediction module, which is used for recording the diffusion tensor within the normal range as a first condition parameter in the suppression state, and predicting the safety boundary of cognitive function decline according to the first condition parameter;

[0050] an abnormality evaluation module, which is used for outputting the diffusion tensor of the cognitive function damage region as a second condition parameter in the abnormal state, and determining the cognitive function decline level according to the second condition parameter.

[0051] and an electronic device, comprising:

[0052] at least one processor;

[0053] and a memory in communication connection with the at least one processor;

[0054] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the cognitive function decline prediction method for type 2 diabetes mellitus.

[0055] The present application has the following technical effects:

[0056] The present application can timely find the decline trend of cognitive function by real-time monitoring and analyzing the cognitive impairment of type 2 diabetes mellitus patients, thereby providing a scientific basis for clinical diagnosis and treatment. Through accurate image processing and data analysis, the present application can effectively predict the safety boundary of cognitive function decline and provide personalized prevention and intervention measures for patients. In addition, the present application can accurately evaluate the level of cognitive function decline according to the diffusion tensor of cognitive impairment, thereby providing an important reference for doctors to develop treatment plans, and ultimately helping to improve the quality of life of type 2 diabetes mellitus patients and reduce the risk of cognitive impairment. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 is a method flowchart of the present application;

[0058] Figure 2 is a system module schematic diagram of the present application;

[0059] Figure 3 is an electronic device structure schematic diagram of the present application. DETAILED DESCRIPTION

[0060] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0061] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the scope of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0062] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. In this specification, "in a preferred embodiment" does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0063] Type 2 diabetes is a common chronic metabolic disease characterized by high blood sugar levels, and long-term high blood sugar can affect multiple systems of the body, including cognitive function, cognitive impairment is one of the common complications of type 2 diabetes patients, which can affect the daily life and work ability of patients, therefore, developing an effective prediction method is of great significance for early intervention and management of cognitive impairment in type 2 diabetes patients.

[0064] Referring to Figure 1 The present application provides a type 2 diabetes cognitive impairment prediction method, comprising:

[0065] S1, preprocessing the acquired brain region image data and outputting as base image data;

[0066] In this step, the cognitive function of type 2 diabetes patients is evaluated by analyzing brain region images, and the brain entropy of T2DM patients with cognitive impairment increases, and there is extensive white matter fiber damage, so by studying brain region images, the cognitive function of T2DM patients can be predicted early, after the brain region image is collected, a series of preprocessing operations are performed on the collected brain image data to ensure the quality and accuracy of the data, the preprocessing steps include but are not limited to denoising, standardization and normalization processing, etc., and finally the preprocessed base image data is output, providing a basis for subsequent analysis;

[0067] Specifically, the step of preprocessing the acquired brain region image data and outputting as base image data comprises:

[0068] S101, collecting brain region image data and adding a time stamp to obtain sample images;

[0069] S102, and denoising the sample images to enhance the contrast of the images;

[0070] S103, standardizing the denoised sample images to unify the format of all sample images, and synchronously recording as base image data;

[0071] In steps S101-S103, in order to ensure the quality and consistency of the brain region image data, a series of preprocessing steps need to be performed on the acquired image data in order to finally output the base image data. First, the image data of the brain region is collected, such as by MRI collection, etc., to capture detailed images of different regions of the brain. After the collection is completed, in order to facilitate subsequent processing and tracking, a timestamp needs to be added to each sample image, so that each sample image will have a unique identifier, recording the time and date of its collection, ensuring the traceability of the data. Then, the sample image with the timestamp is denoised. Various noises may be introduced during the imaging process, such as device noise, environmental noise, etc. Specific methods include Gaussian filtering, median filtering, etc., to remove random noise in the image while preserving the detail information of the image. After denoising, the contrast of the image is further enhanced, making the different tissues and structures in the sample image more clearly visible, to achieve a better visual effect. Finally, the sample image after denoising and contrast enhancement is standardized. The purpose of standardization is to unify the format of all sample images, ensuring that they are consistent in size, resolution, and color space, etc. This includes adjusting the size of the image to conform to the pre-set standard size, adjusting the resolution of the image to ensure that all images have the same pixel density, and converting the color space of the image to meet the needs of subsequent processing. After completing the standardization process, the processed sample image is recorded as base image data, which can be used for subsequent analysis and research.

[0072] S2, feature extraction is performed on the base image data to obtain brain region feature images related to cognitive function;

[0073] In this step, corresponding image processing techniques such as edge detection, texture analysis, etc. are used to extract features from the pre-processed base image that can reflect the cognitive function status. For example, the brain entropy of T2DM patients increases, and there is widespread white matter fiber damage. Through feature extraction, brain region feature images that need to be analyzed can be further extracted.

[0074] S3, mark the cognitive function damage area and non-damage area in the brain region feature area, and monitor the diffusion tensor of the cognitive function damage area in real time;

[0075] In this step, by comparing and analyzing the diffusion tensor of the damaged area and the non-damaged area, the specific brain area of cognitive impairment can be more accurately located. Using corresponding image recognition technology, such as diffusion tensor imaging (DTI) technology, the brain area feature image can be further analyzed to identify the area of cognitive impairment. DTI technology can provide information about the microstructure of white matter fiber bundles in the brain. By measuring the diffusion of water molecules in brain tissue, the integrity and directionality of white matter fibers can be revealed. In the area of cognitive impairment, due to the damage of white matter fibers, the diffusion pattern of water molecules will show abnormalities, which can be identified through abnormal signals in the DTI image. By monitoring the changes of these diffusion tensors in real time, the diffusion tensor of the damaged area can be monitored in real time, and the trend of the damaged area over time can be observed, thus providing dynamic data support for predicting cognitive decline. In addition, by comparing the diffusion tensor images at different time points, the progress speed and degree of cognitive impairment can be evaluated, providing scientific basis for clinical diagnosis and treatment.

[0076] Specifically, the step of real-time monitoring the diffusion tensor of the cognitive impairment area includes:

[0077] S301, obtaining the edge curve of the cognitive impairment area;

[0078] S302, constructing a virtual coordinate system, and recording the coordinates of each edge corner in the virtual coordinate system in the statistical edge curve as a reference coordinate parameter;

[0079] S303, calculating the damage area of the cognitive impairment area according to the reference coordinate parameter;

[0080] S304, constructing a monitoring period and setting multiple monitoring nodes within the monitoring period, and real-time collecting the damage area of the cognitive impairment area under each monitoring node;

[0081] S305, difference processing the cognitive impairment area under adjacent monitoring nodes to obtain the diffusion tensor of the cognitive impairment area;

[0082] In steps S301-S305, when collecting the diffusion tensor of the cognitive impairment area, first, the edge curve of the cognitive impairment area needs to be obtained, and the initial profile information of the cognitive impairment area is determined. The edge curve can be obtained by image processing technology, such as edge detection algorithm to identify the boundary between the impairment area and normal tissue. Then a virtual coordinate system needs to be constructed. In this virtual coordinate system, the coordinate positions of each edge corner point in the edge curve are counted. In this way, the coordinates of the edge corner points can be recorded as the reference coordinate parameters. After the reference coordinate parameters, the impairment area of the cognitive impairment area is calculated according to the reference coordinate parameters. Then a monitoring period needs to be constructed. In the monitoring period, multiple monitoring nodes are set synchronously, and the impairment area of the cognitive impairment area under each monitoring node is collected in real time. Finally, the cognitive impairment area under adjacent monitoring nodes is processed by difference, so that the diffusion tensor of the cognitive impairment area can be obtained.

[0083] S4, the diffusion tensor of the cognitive impairment area is analyzed periodically, and the cognitive impairment state is output synchronously, wherein the cognitive impairment state includes inhibition state and abnormal state.

[0084] In this step, by comparing the diffusion tensors of different stages, the progress of cognitive impairment can be analyzed periodically. For example, by comparing the diffusion tensors of consecutive monitoring nodes, the diffusion speed and range of the cognitive impairment area over time can be observed, so as to determine the inhibition state or abnormal state of cognitive impairment. The inhibition state may indicate that the progress of cognitive impairment is slow or temporarily stable, while the abnormal state may indicate that the progress of cognitive impairment is rapid or deteriorating. Through periodic analysis, important information about the trend of cognitive impairment of patients can be provided to doctors, which helps to develop more personalized treatment plans.

[0085] Specifically, the step of periodically analyzing the diffusion tensor of the cognitive impairment area and synchronously outputting the cognitive impairment state includes:

[0086] S401, in the monitoring period, multiple equally spaced parallel periods are set;

[0087] S402, the diffusion tensor of the cognitive impairment area in each parallel period is counted and recorded as a state evaluation parameter;

[0088] S403, the state evaluation threshold is obtained, and the state evaluation threshold is compared with the state evaluation parameter;

[0089] When the state evaluation parameter is less than the state evaluation threshold, it indicates that the diffusion of the cognitive impairment area is inhibited, and the cognitive impairment state is recorded as the inhibition state;

[0090] When the state evaluation threshold is greater than or equal to the state evaluation threshold, it indicates that the diffusion of the cognitive impairment area is not inhibited, and the cognitive decline state is recorded as an abnormal state;

[0091] In steps S401-S403, when the cognitive impairment area of the patient's brain is analyzed in stages, first, a plurality of equally spaced parallel periods are set in the monitoring period, so as to evaluate the diffusion tensor in stages, in each parallel period, the diffusion tensor of the cognitive impairment area is counted and recorded as a state evaluation parameter, which will be compared with the pre-set state evaluation threshold to determine whether the diffusion of the cognitive impairment is inhibited, if the state evaluation parameter is greater than the state evaluation threshold, it indicates that the diffusion of the cognitive impairment is inhibited, at this time, the cognitive decline state is recorded as an inhibition state, on the contrary, if the state evaluation threshold is greater than or equal to the state evaluation parameter, it indicates that the diffusion of the cognitive impairment is not inhibited, at this time, the cognitive decline state is recorded as an abnormal state, based on this, the stage analysis result of the patient's cognitive decline can be obtained, thereby helping the doctor to provide a more accurate treatment plan for the patient;

[0092] S5, in the inhibition state, the diffusion tensor of the cognitive impairment area is within the normal range, and the diffusion tensor within the normal range is recorded as a first condition parameter, and the safety boundary of the cognitive decline is predicted according to the first condition parameter;

[0093] In this step, when the cognitive decline state of the patient is in the inhibition state, the diffusion tensor is monitored in real time, a personalized treatment plan can be provided for the patient to prevent further decline of cognitive function, in this step, the diffusion tensor within the normal range is recorded as a first condition parameter, in the inhibition state, by recording the diffusion tensor within the normal range, a safety boundary can be established, according to the first condition parameter, the safety boundary of the cognitive decline can be predicted, which reflects the potential risk of cognitive impairment, thereby helping the doctor to evaluate the treatment effect and timely adjust the treatment plan to ensure that the patient receives the best medical care;

[0094] Specifically, the step of predicting the safety boundary of the cognitive decline according to the first condition parameter comprises:

[0095] S501, obtaining the first condition parameter and arranging the first condition parameter according to the occurrence sequence;

[0096] S502, obtaining an evaluation function, and inputting the first condition parameter into the evaluation function according to the arrangement order of the first condition parameter, and recording the output result of the evaluation function as a trend condition parameter;

[0097] S503, obtaining an allowable decline area corresponding to the first condition parameter;

[0098] S504, acquire the prediction function, input the allowable reduction area and the trend condition parameter into the prediction function, and record the output result of the prediction function as the prediction safety interval;

[0099] S505, offset the last output node of the first condition parameter according to the prediction safety interval, and obtain the safety boundary of the first condition parameter predicting cognitive function reduction;

[0100] In steps S501-S505, after the output of the first condition parameter, it is arranged according to the occurrence time sequence (specifically, a time stamp can be added to the first condition parameter in advance), so as to analyze the change trend of the diffusion tensor with time. The evaluation function will predict the trend of cognitive function reduction according to the arranged first condition parameter, and the output result is the trend condition parameter. The expression of the evaluation function is: In the formula, R represents the trend condition parameter, T represents the time length of the parallel period, m represents the number of the first condition parameters, K j and K j-1 represent the first condition parameters of adjacent arrangement positions. Then, the allowable reduction area corresponding to the first condition parameter needs to be acquired. The allowable reduction area is a safety threshold determined based on clinical experience or previous research. By inputting the allowable reduction area and the trend condition parameter into the prediction function, the prediction safety interval can be obtained. The expression of the prediction function is: In the formula, t represents the prediction safety interval, K r represents the allowable reduction area, K d represents the first condition parameter of the last arrangement position. The prediction safety interval reflects the possible safety time range of cognitive impairment. Finally, the last output node of the first condition parameter is offset processed according to the prediction safety interval, so as to obtain the safety boundary of the first condition parameter predicting cognitive function reduction. Of course, after the output of the prediction safety interval, it can also be offset downward to reduce the prediction error. The specific adjustment range can be adjusted according to actual needs. In this way, the doctor can have a clear understanding of the cognitive function reduction trend of the patient, and accordingly formulate or adjust the treatment plan, so as to achieve the best treatment effect.

[0101] S6, in the abnormal state, the diffusion tensor of the cognitive impairment area is abnormal, and is output as the second condition parameter at the same time. The cognitive function reduction level is determined according to the second condition parameter.

[0102] In this step, when the cognitive function decline state of the patient is an abnormal state, the diffusion tensor of the cognitive impairment area is recorded as a second condition parameter, which reflects the severity of the cognitive impairment. By analyzing the second condition parameter, the specific level of cognitive function decline can be determined, thereby providing targeted treatment measures for the patient.

[0103] Specifically, the step of determining the cognitive function decline level according to the second condition parameter comprises:

[0104] S601, obtaining a second condition parameter;

[0105] S602, obtaining a classification interval, wherein the classification interval is provided with a plurality of classification intervals, and each classification interval corresponds to a cognitive function decline level;

[0106] S603, pairing the second condition parameter with the classification interval, and matching the corresponding cognitive function decline level;

[0107] In steps S601-S603, after the second condition parameter is output, the numerical value of the second condition parameter is compared with the classification interval to determine the specific level of cognitive function decline. The classification interval is set according to clinical data and previous research. Each classification interval corresponds to a different degree of cognitive function decline. By matching the second condition parameter with the classification interval, the current cognitive function decline level of the patient can be accurately identified. For example, if the second condition parameter falls within a lower classification interval, it indicates that the degree of cognitive function decline is lighter. Conversely, if it falls within a higher classification interval, it indicates that the degree of cognitive function decline is heavier. After determining the cognitive function decline level, the doctor can develop a more accurate treatment plan for the patient to improve the patient's cognitive function state.

[0108] In a preferred embodiment, the step of calculating the damage area of the cognitive impairment area according to the reference coordinate parameter comprises:

[0109] Obtaining a reference coordinate parameter of the cognitive impairment area;

[0110] Obtaining a preset calculation function;

[0111] Inputting the reference coordinate parameter into the calculation function, and recording the output result of the calculation function as the cognitive impairment area.

[0112] In this embodiment, to calculate the damage area of the cognitive impairment area, the reference coordinate parameter of the cognitive impairment area and the preset calculation function are first obtained, and then the reference coordinate parameter is input into the calculation function to obtain an output result representing the damage area of the cognitive impairment area. The calculation formula of the cognitive impairment area is: In the formula, S rs represents the area of the cognitive impairment region, n represents the number of edge corner points, a i and a i+1 both represent the horizontal coordinates of the edge corner points, b i and b i+1 represent the vertical coordinates of the edge corner points.

[0113] In a preferred embodiment, after the trend condition parameter is output, it is compared with a preset standard trend value, and when the trend condition parameter exceeds the standard trend value, the prediction of the safety boundary of cognitive impairment is stopped, and the inhibition state is converted to an abnormal state, otherwise, the prediction of the safety boundary of cognitive impairment is continued.

[0114] In this embodiment, after the trend condition parameter is output, it is compared with a preset standard trend value to ensure whether the current trend condition parameter is within an acceptable range. If it is found in the comparison process that the trend condition parameter exceeds the range of the standard trend value, measures are immediately taken to stop the prediction of the safety boundary of cognitive impairment, and at the same time, the current inhibition state is converted to an abnormal state for further analysis and processing. On the contrary, if the trend condition parameter does not exceed the standard trend value, the system continues to perform the prediction of the safety boundary of cognitive impairment to ensure the smooth progress of the whole process.

[0115] Referring to Figure 2 , a cognitive impairment prediction system for type 2 diabetes, using the type 2 diabetes cognitive impairment prediction method described above, comprising:

[0116] An image processing module, which is used to pre-process the acquired brain region image data and output as base image data;

[0117] A feature extraction module, which is used to extract features from the base image data to obtain cognitive function-related brain region feature images;

[0118] A marking module, which is used to mark the cognitive impairment region and the non-impairment region in the brain region feature region, and real-time monitor the diffusion tensor of the cognitive impairment region;

[0119] A state evaluation module, which is used to analyze the diffusion tensor of the cognitive impairment region in stages and synchronously output the cognitive impairment state, wherein the cognitive impairment state includes an inhibition state and an abnormal state;

[0120] The prediction module is configured to record the diffusion tensor in the normal range as a first condition parameter in the inhibition state, and predict the safe boundary of cognitive decline according to the first condition parameter.

[0121] The abnormality evaluation module is configured to output the diffusion tensor of the cognitive impairment region as a second condition parameter in the abnormal state, and determine the cognitive decline level according to the second condition parameter.

[0122] As described above, the system includes an image processing module, a feature extraction module, a marking module, a state evaluation module, a prediction module and an abnormality evaluation module. The image processing module is responsible for the preliminary preprocessing of the collected brain image data. This process includes image denoising, enhancement and standardization steps, and the purpose is to ensure the accuracy and reliability of subsequent processing. After processing, the image processing module outputs high-quality base image data, providing a solid foundation for subsequent analysis. The feature extraction module extracts key features from the base image data and outputs brain region feature images that reflect specific changes in brain regions. The marking module further works on the basis of feature extraction, specifically marking the cognitive impairment region and the non-impairment region in the brain region feature image, and can also continuously track the diffusion of the cognitive impairment region to provide dynamic impairment diffusion tensor information for doctors and researchers. The core function of the state evaluation module is to analyze the diffusion tensor of the cognitive impairment region at different stages. Through this analysis, the current cognitive decline state of the patient can be output synchronously. The cognitive decline state includes the inhibition state and the abnormal state, each of which corresponds to different cognitive decline degrees and characteristics. The prediction module executes in the inhibition state, specifically recording the diffusion tensor in the normal range as a first condition parameter. Based on the first condition parameter, the prediction module can predict the safe boundary of cognitive decline, thereby providing an important reference for clinical intervention. The abnormality evaluation module executes in the abnormal state, outputs the diffusion tensor of the cognitive impairment region as a second condition parameter, and determines the specific level of cognitive decline according to these parameters, which is of great significance for developing personalized treatment plans and management plans.

[0123] Please refer to Figure 3 An electronic device, the electronic device comprising:

[0124] at least one processor;

[0125] and a memory connected in communication with the at least one processor;

[0126] wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the cognitive decline prediction method for type 2 diabetes described above.

[0127] The processor of the electronic device described above can be a central processing unit (CPU) or a graphics processing unit (GPU) for processing complex computing tasks and image data. The memory can be a random access memory (RAM) or a solid state drive (SSD) for storing program codes and temporary data. The computer program contains a series of instructions executed by the processor to achieve the prediction of cognitive decline in type 2 diabetes patients, and the electronic device can also include an arithmetic unit, an input device and an output device to ensure efficient operation of the entire prediction process. The arithmetic unit of the electronic device is responsible for performing specific mathematical and logical operations, the input device such as a keyboard and a mouse allows the user to interact with the system, and the output device such as a display and a printer is used to display the prediction results and related data.

[0128] It should be noted that in this paper, the term "including", "containing" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, device, article or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, device, article or method. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0129] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should also be considered as the protection scope of the present application. The structures, devices and operation methods not specifically described and explained in the present application, such as without special description and limitation, are implemented according to the conventional means in the art.

Claims

1. A method of predicting cognitive decline in type 2 diabetes, characterized by: The method comprises the following steps: preprocessing the acquired brain region image data and outputting the same as base image data; extracting features from the base image data to obtain brain region feature images related to cognitive function; labeling cognitive impairment regions and non-impairment regions in the brain region feature regions and monitoring the diffusion tensor of the cognitive impairment regions in real time; performing periodic analysis on the diffusion tensor of the cognitive impairment regions and synchronously outputting cognitive decline states, wherein the cognitive decline states include inhibition states and abnormal states; in the inhibition state, the diffusion tensor of the cognitive impairment regions is within a normal range, the diffusion tensor within the normal range is recorded as a first condition parameter, and the safety boundary of cognitive decline is predicted according to the first condition parameter; in the abnormal state, the diffusion tensor of the cognitive impairment regions is abnormal, and the same is synchronously outputted as a second condition parameter, and the cognitive decline level is determined according to the second condition parameter; wherein the step of monitoring the diffusion tensor of the cognitive impairment regions in real time comprises: acquiring the edge curve of the cognitive impairment regions; constructing a virtual coordinate system, and recording the coordinates of each edge corner point in the virtual coordinate system as a reference coordinate parameter through statistics; calculating the impairment area of the cognitive impairment regions according to the reference coordinate parameter; constructing a monitoring period and setting multiple monitoring nodes in the monitoring period, and collecting the impairment area of the cognitive impairment regions under each monitoring node in real time; performing difference processing on the cognitive impairment areas under adjacent monitoring nodes to obtain the diffusion tensor of the cognitive impairment regions; the step of calculating the impairment area of the cognitive impairment regions according to the reference coordinate parameter comprises: acquiring the reference coordinate parameter of the cognitive impairment regions; acquiring a preset calculation function; inputting the reference coordinate parameter into the calculation function, and recording the output result of the calculation function as the impairment area of the cognitive impairment regions.

2. The method of claim 1, wherein the cognitive impairment in type 2 diabetes is predicted by the method comprising: a) measuring the level of the biomarker in a sample obtained from the subject; and b) comparing the level of the biomarker in the sample to a reference level of the biomarker. The step of preprocessing the acquired brain region image data and outputting the same as base image data comprises: collecting the brain region image data and adding a time stamp to obtain sample images; and enhancing the contrast of the images through denoising processing; standardizing the denoised sample images to unify the formats of all the sample images and synchronously recording the same as base image data.

3. The method of claim 1, wherein the cognitive impairment in type 2 diabetes is predicted by the method comprising: a) measuring the level of the biomarker in a sample obtained from the subject; and b) comparing the level of the biomarker in the sample to a reference level of the biomarker. The step of performing periodic analysis on the diffusion tensor of the cognitive impairment regions and synchronously outputting cognitive decline states comprises: setting multiple equally spaced parallel periods within the monitoring period; statistically analyzing the diffusion tensor of the cognitive impairment regions in each parallel period and recording the same as a state evaluation parameter; acquiring a state evaluation threshold and comparing the state evaluation threshold with the state evaluation parameter; when the state evaluation parameter is less than the state evaluation threshold, it indicates that the diffusion of the cognitive impairment regions is inhibited, and the cognitive decline state is recorded as an inhibition state; When the state evaluation threshold is greater than or equal to the state evaluation threshold, it indicates that the spread of the cognitive impairment area is not inhibited, and the cognitive decline state is recorded as an abnormal state.

4. The method of claim 1, wherein the cognitive impairment in type 2 diabetes is predicted by the method comprising: a) measuring the level of the biomarker in a biological sample obtained from the subject; and b) comparing the level of the biomarker in the biological sample to a reference level of the biomarker. The step of predicting the safety boundary of cognitive decline according to the first condition parameter comprises: obtaining the first condition parameter and arranging the first condition parameter according to the occurrence time sequence; obtaining an evaluation function and inputting the first condition parameter into the evaluation function according to the arrangement order of the first condition parameter, and recording the output result of the evaluation function as a trend condition parameter; obtaining the allowable decline area corresponding to the first condition parameter; obtaining a prediction function and inputting the allowable decline area and the trend condition parameter into the prediction function, and recording the output result of the prediction function as a predicted safety interval; According to the predicted safety interval, the last output node of the first condition parameter is offset to obtain the safety boundary of the first condition parameter for predicting cognitive decline.

5. The method of claim 4, wherein the cognitive impairment in type 2 diabetes is predicted by the method comprising: a) measuring the level of the biomarker in a sample obtained from the subject; and b) comparing the level of the biomarker in the sample to a reference level of the biomarker. After the trend condition parameter is output, it is compared with a preset standard trend value, and when the trend condition parameter exceeds the standard trend value, the prediction of the safety boundary of cognitive decline is stopped, and the inhibition state is converted into an abnormal state, otherwise, the prediction of the safety boundary of cognitive decline is continued.

6. The method of claim 1, wherein the cognitive impairment in type 2 diabetes is predicted by the method. The step of determining the cognitive decline level according to the second condition parameter comprises: obtaining the second condition parameter; obtaining a classification interval, wherein the classification interval is provided with a plurality of classification intervals, and each classification interval corresponds to a cognitive decline level; pairing the second condition parameter with the classification interval to match the corresponding cognitive decline level.

7. A system for predicting cognitive decline in type 2 diabetes, characterized by: The method for predicting cognitive decline of type 2 diabetes mellitus according to any one of claims 1-6 comprises: an image processing module for pre-processing the obtained brain region image data and outputting the base image data; a feature extraction module for extracting features from the base image data to obtain brain region feature images related to cognitive function; a marking module for marking cognitive impairment areas and non-impairment areas in the brain region feature area, and monitoring the diffusion tensor of the cognitive impairment area in real time; a state evaluation module for periodically analyzing the diffusion tensor of the cognitive impairment area and synchronously outputting a cognitive decline state, wherein the cognitive decline state comprises an inhibition state and an abnormal state; a prediction module for recording the diffusion tensor within the normal range as a first condition parameter in the inhibition state, and predicting the safety boundary of cognitive decline according to the first condition parameter; an abnormality evaluation module for outputting the diffusion tensor of the cognitive impairment area as a second condition parameter in the abnormal state, and determining the cognitive decline level according to the second condition parameter.

8. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for predicting cognitive decline in type 2 diabetes mellitus according to any one of claims 1 to 6.

Images