Early diagnosis system for Parkinson's disease based on eye movement feature analysis

Abstract

The present invention discloses an early diagnosis system for Parkinson's disease based on eye movement feature analysis, relating to the technical field of Parkinson's disease diagnosis. This system aims to address the problem that, while eye and facial movement parameters may change in Parkinson's disease, these changes may also occur in other neurodegenerative diseases or during normal aging. Furthermore, high-precision eye and facial motion capture data is complex and often fails to accurately capture the characteristics of early Parkinson's disease diagnosis, thus affecting diagnostic accuracy and efficiency. By accurately capturing and analyzing a patient's eye movement data and facial expression video images, the system can effectively distinguish Parkinson's disease from other diseases that may cause similar symptoms, reducing misdiagnosis and missed diagnoses. Incorporating pupillary distance and refractive power information ensures data standardization and comparability, improving diagnostic consistency and reliability, and enabling patients to receive early diagnosis, thereby receiving treatment as soon as possible, improving treatment efficacy and quality of life.

Description

Technical Field

[0001] The present invention relates to the technical field of Parkinson's disease diagnosis, and in particular to an early diagnosis system for Parkinson's disease based on eye movement feature analysis. Background Art

[0002] Traditional Parkinson's disease diagnosis methods mostly rely on the observation of clinical symptoms and subjective judgment, lacking quantitative indicators, which is not conducive to early identification and evaluation of treatment effects. Regarding the early diagnosis of Parkinson's disease, the patent application with publication number: CN115251901A discloses an early diagnosis method for Parkinson's disease based on eye and face motion capture technology, including: first, collecting the test subject's eye and face movement parameters, including the following parameters: (1) the frequency, speed, and amplitude of horizontal and vertical eye saccades and blinks; (2) the amplitude, speed, and frequency of contraction of the frontalis and cheek muscles; (3) the frequency, speed, and amplitude of contraction of the corners of the mouth and lips; (4) the amplitude and frequency of head movement; and (5) the time it takes for facial muscles to go from static to dynamic to recovery to static.

[0003] Although the above patent can realize the diagnosis of patients with Parkinson's syndrome, although the eye and facial movement parameters may change in Parkinson's disease, changes in these parameters may also occur in other neurodegenerative diseases or normal aging. In addition, high-precision eye and facial motion capture data is complex and often cannot accurately capture the characteristics of early diagnosis of Parkinson's disease, affecting the accuracy and efficiency of diagnosis. Summary of the Invention

[0004] The purpose of the present invention is to provide an early diagnosis system for Parkinson's disease based on eye movement feature analysis. By combining facial expression analysis, the system more comprehensively evaluates the patient's symptoms, improves the accuracy of diagnosis, and combines pupil distance information and refractive power information to explain abnormalities in eye movements, thereby improving the consistency and reliability of diagnosis, thereby solving the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The Parkinson's disease early diagnosis system based on eye movement feature analysis includes:

[0007] a data acquisition unit, configured to capture the patient's eye movement data in real time based on an eye tracker, and to collect the patient's facial expression and eye movement video data in real time based on a camera on the eye tracker, and to process the acquired eye movement data and facial expression and eye movement video data;

[0008] a feature extraction unit, configured to extract eye movement features related to Parkinson's disease from the processed data, including eye movement speed, movement amplitude, eye fixation stability, and eye saccadic movement features;

[0009] The early diagnosis unit is used to train and model the extracted eye movement features, establish an early diagnosis model for Parkinson's disease, input the extracted patient's eye movement features into the early diagnosis model for Parkinson's disease, obtain the early diagnosis results of Parkinson's disease, and generate an early diagnosis report for Parkinson's disease.

[0010] Furthermore, the data acquisition unit includes:

[0011] The motion stimulation module is used to establish a visual stimulation pattern according to the diagnostic requirements of Parkinson's disease, generate dynamic visual stimulation according to the preset visual stimulation pattern, and display the dynamic visual stimulation on the display screen in real time to generate a saccade task;

[0012] A data acquisition module is used to record the patient's eye movement data in real time based on an eye tracker when the patient performs a saccade task, including the start and end time, speed, amplitude and path of the saccade;

[0013] an image acquisition module for capturing video images of the patient's eye movements and the patient's facial expressions during the eye movements;

[0014] The data processing module is used to pre-process the data collected by the data acquisition module and the image acquisition module and convert the data into a unified format.

[0015] Furthermore, the data processing module further includes:

[0016] Capturing a video image of the patient's eyeball movement based on an image acquisition module, extracting the patient's eyeball image data, and calculating the distance between the two pupils of the patient and the shape ratio of the two eyeballs;

[0017] The eye image data of at least one patient is calculated, and based on the calculation results, the interpupillary distance is compared to determine whether it is consistent, and whether the variation range of the interpupillary distance is abnormal;

[0018] According to the judgment result, the average value of the calculated results is used as the distance between the two pupils of the patient to obtain the final pupil distance information of the patient;

[0019] The refractive power information of the patient is obtained by calculation according to the shape ratio of the two eyeballs of the patient.

[0020] Furthermore, the feature extraction unit includes:

[0021] An eye movement feature extraction module is used to extract the patient's eye movement speed features and eye movement amplitude features, and to modify the eye movement speed features and eye movement amplitude features based on the patient's final pupil distance information;

[0022] The eye gaze feature extraction module is used to extract the patient's eye gaze point features and eye saccadic movement features, and evaluate the visual function and motor ability of the eye gaze point features and eye saccadic movement features based on the patient's refractive information.

[0023] Furthermore, the early diagnosis unit includes:

[0024] A diagnostic model building module is used to build an early diagnosis model for Parkinson's disease and train the model based on the output data of the eye movement feature extraction module and the eye gaze feature extraction module;

[0025] An eye movement abnormality feature extraction module is used to extract asymmetric features of saccadic eye movements based on the results of visual function and motor ability assessment, including: saccadic latency asymmetry: comparing the reaction time difference between the left and right eyes in a saccadic task; saccadic peak velocity asymmetry: comparing the maximum velocity difference between the left and right eyes during a saccadic process; saccadic amplitude asymmetry: and the difference in movement distance of the left and right eyes during a saccadic process. The degree of eye movement abnormality of the patient is assessed based on the asymmetric features;

[0026] The Parkinson's disease diagnosis module is used to input the extracted eye movement abnormality features into a trained Parkinson's disease early diagnosis model for diagnosis, and output a diagnosis result including an asymmetry index and conclusion based on the evaluation results of the patient's eye movement abnormality level;

[0027] The clinical diagnosis result comparison module is used to compare the diagnosis results output by the Parkinson's disease diagnosis module with the diagnosis results of clinicians, and adjust the parameters of the Parkinson's disease early diagnosis model based on the comparison results.

[0028] Furthermore, the eye movement abnormality feature extraction module is specifically:

[0029] identifying saccadic events in eye movement data of a patient captured by an eye tracker based on saccadic eye movement features, and segmenting the continuous eye movement data into individual saccadic events based on the identification result;

[0030] Calculate the latency, peak velocity, and amplitude of each saccade event, and compare the differences between the left and right eyes. Calculate the mean and standard deviation of the saccade latency, peak velocity, and amplitude of the left and right eyes based on the comparison results. Obtain the asymmetry index of latency, peak velocity, and amplitude based on the calculation results.

[0031] The asymmetry index of latency, peak velocity, and amplitude is compared with the corresponding preset asymmetry index threshold to determine whether there is significant asymmetry between the left and right eyes, and to comprehensively assess the degree of eye movement abnormality in the patient.

[0032] Furthermore, the Parkinson's disease diagnosis module also includes determining whether the patient has Parkinson's disease based on the video image of the patient's facial expression during eye movement, specifically:

[0033] obtaining a plurality of facial expression sample data of the patient based on the video image;

[0034] Extract the patient's blinking frequency, facial movement change frequency and amplitude changes from each facial expression sample data;

[0035] Identify the extracted multiple parameters, obtain identification results, and determine whether there are typical facial movement features of Parkinson's disease;

[0036] The abnormal coefficient of the patient is calculated based on the blinking frequency, facial movement change frequency and amplitude change of the patient in each facial expression sample data and the identification result of each parameter;

[0037] Confirm whether the abnormal coefficient is greater than a preset coefficient. If so, obtain an abnormal video image segment of the patient based on the video image. Otherwise, preliminarily determine that the patient does not suffer from Parkinson's disease.

[0038] Furthermore, obtaining an abnormal video image segment of the patient based on the video image further includes:

[0039] Extracting human eye feature factors in each frame of image based on abnormal video image segments;

[0040] The typical features of Parkinson's disease are screened out based on the human eye characteristic factors in each frame of the image;

[0041] The severity of the patient's symptoms is calculated based on the typical features of Parkinson's disease in the human eye feature factors in each frame of the image;

[0042] Confirm whether the severity of the patient's symptoms is greater than or equal to a preset threshold. If so, it is confirmed that the patient has Parkinson's disease. Otherwise, it is considered that the patient does not show typical symptoms of Parkinson's disease.

[0043] Furthermore, the data acquisition unit includes:

[0044] Compensation modules for:

[0045] Collect environmental images based on the camera on the eye tracker;

[0046] Extracting brightness component information of each pixel in the environment image; determining a brightness histogram based on the brightness component information of each pixel in the environment image; determining a brightness interval based on the brightness histogram, determining a median value of the brightness interval, and counting a first number of pixels greater than the median value and a second number of pixels less than the median value; and generating and executing a lighting compensation instruction when it is determined that the second number is greater than the first number;

[0047] in, is the grayscale value of the environment image G at (x, y) after illumination compensation; is the grayscale value of the environment image G at (x, y); is the target grayscale mean generated based on illumination compensation; The number of pixels included in the environment image;

[0048] Adjustment module for:

[0049] changing a propagation direction of the laser beam based on a first angle of rotation of the eye tracker so that the laser beam path passes through the patient's face, and adjusting a first angular resolution of capturing the patient's facial expression based on the first angle of rotation of the eye tracker;

[0050]

[0051] in, is the first angular resolution; is an integer, , is the laser beam divergence angle; is the first angle between the eye tracker and the patient's face; is the maximum angle the eye tracker can rotate; is the initial angular resolution of the eye tracker;

[0052] Changing a propagation direction of the laser beam based on a second angle of rotation of the eye tracker so that the laser light path passes through the patient's eyeball, and adjusting a second angular resolution of capturing the patient's eyeball according to the second angle of rotation of the eye tracker;

[0053]

[0054] in, is the second angular resolution; The second angle between the eye tracker and the patient's eyeball;

[0055] The camera on the eye tracker collects video data of the patient's facial expressions and eye movements based on the first angular resolution and the second angular resolution.

[0056] Furthermore, the image acquisition module includes:

[0057] The first determining module is configured to:

[0058] Performing frame processing on the video image of the patient's facial expression during eye movement to obtain a number of sub-frame images;

[0059] Performing grayscale processing on a plurality of frames of sub-images to obtain a plurality of frames of grayscale images;

[0060] Traverse each pixel on the grayscale image, add up the grayscale values ​​of each pixel, and divide the total grayscale value by the total number of pixels to obtain an average grayscale value; in the process of traversing each pixel on the grayscale image, record the maximum grayscale value and the minimum grayscale value; determine the pixel whose grayscale value is less than the average grayscale value and calculate a first grayscale sum value; determine the pixel whose grayscale value is greater than the average grayscale value and calculate a second grayscale sum value;

[0061] Calculating a feature value of the grayscale image based on the maximum grayscale value, the minimum grayscale value, the first grayscale sum value, and the second grayscale sum value;

[0062]

[0063] in, is the eigenvalue of the grayscale image; is the second grayscale value; is the first grayscale value; is the maximum grayscale value; is the minimum grayscale value; comparing the characteristic value of the grayscale image with the preset characteristic threshold, screening out the grayscale images whose characteristic value is greater than the preset characteristic threshold, and determining them as the target image set;

[0064] The second determining module is configured to:

[0065] Determine a first target image and a second target image of adjacent frames in the target image set;

[0066] Acquire a first grayscale feature and a first texture feature of a first target image; acquire a first grayscale feature and a second texture feature of a second target image;

[0067] performing a first image registration on the first target image and the second target image based on the first grayscale feature and the second grayscale feature, and determining first change information of the facial expression according to a result of the first image registration;

[0068] performing a second image registration on the first target image and the second target image based on the first texture feature and the second texture feature, and determining second change information of the facial expression according to a result of the second image registration;

[0069] Determine facial expression change information based on the first change information and the second change information.

[0070] Compared with the prior art, the present invention has the following beneficial effects:

[0071] By accurately capturing and analyzing patients' eye movement data and facial expression video images, it is possible to effectively distinguish Parkinson's disease from other diseases that may cause similar symptoms, reducing misdiagnosis and missed diagnosis. At the same time, combining pupil distance information and refractive power information ensures data standardization and comparability, improves diagnostic consistency and reliability, and enables patients to be diagnosed in the early stages of the disease, thereby receiving treatment as soon as possible, potentially slowing disease progression, and improving treatment outcomes and quality of life. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 This is a module diagram of the Parkinson's disease early diagnosis system based on eye movement feature analysis of the present invention. DETAILED DESCRIPTION

[0073] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0074] To address the technical issues that although eye and facial movement parameters may change in Parkinson's disease, changes in these parameters may also occur in other neurodegenerative diseases or normal aging, and high-precision eye and facial motion capture data is complex and often cannot accurately capture the characteristics of early diagnosis of Parkinson's disease, affecting the accuracy and efficiency of diagnosis, please refer to Figure 1 , this embodiment provides the following technical solutions,

[0075] The Parkinson's disease early diagnosis system based on eye movement feature analysis includes:

[0076] a data acquisition unit, configured to capture the patient's eye movement data in real time based on an eye tracker, and to collect the patient's facial expression and eye movement video data in real time based on a camera on the eye tracker, and to process the acquired eye movement data and facial expression and eye movement video data;

[0077] A feature extraction unit is used to extract eye movement features related to Parkinson's disease from the processed data, including eye movement speed, movement amplitude, eye gaze point stability and eye saccadic movement features, including:

[0078] An eye movement feature extraction module is used to extract the patient's eye movement speed features and eye movement amplitude features, and to modify the eye movement speed features and eye movement amplitude features based on the patient's final pupil distance information;

[0079] The eye gaze feature extraction module is used to extract the patient's eye gaze point features and eye saccadic movement features, and evaluate the visual function and motor ability of the eye gaze point features and eye saccadic movement features based on the patient's refractive information.

[0080] In this embodiment, the device is calibrated based on the pupillary distance information to ensure that eye movement measurements are performed in the correct coordinate system. Corrected standardized data is obtained, making the data of different patients comparable when analyzing eye movement data. The patient's refractive information helps interpret abnormalities in eye movement. For example, myopia or hyperopia may affect the performance of eye tracking tasks. Visual function and motor ability assessments are performed to more accurately reflect the patient's actual visual ability. If the patient has significant saccadic asymmetry, combining refractive information can help determine whether this is due to a visual problem or a motor symptom of Parkinson's disease.

[0081] The early diagnosis unit is used to train and model the extracted eye movement features, establish an early diagnosis model for Parkinson's disease, input the extracted patient's eye movement features into the early diagnosis model for Parkinson's disease, obtain the early diagnosis results of Parkinson's disease, and generate an early diagnosis report for Parkinson's disease.

[0082] In this embodiment, by comprehensively analyzing eye movement characteristics, Parkinson's disease can be distinguished from other diseases that may cause similar eye movement abnormalities, thereby reducing misdiagnosis. Early diagnosis allows patients to receive treatment earlier, which may slow disease progression and improve treatment efficacy. By calibrating the equipment based on pupillary distance information, data standardization is ensured, making data from different patients comparable, and improving the consistency and reliability of diagnosis. Combined with the patient's refractive information, it can better explain abnormalities in eye movements and distinguish whether they are due to visual problems or motor symptoms of Parkinson's disease. The detailed diagnostic report provides doctors with an objective and quantitative basis for diagnosis, which helps doctors develop personalized treatment plans based on the patient's specific situation.

[0083] In this embodiment, the data acquisition unit includes:

[0084] The motion stimulation module is used to establish visual stimulation patterns based on the diagnostic requirements of Parkinson's disease, such as random point displacement and target tracking. It generates dynamic visual stimulation according to the preset visual stimulation patterns and displays the dynamic visual stimulation on the display in real time to generate a saccade task.

[0085] A data acquisition module is used to record the patient's eye movement data in real time based on an eye tracker when the patient performs a saccade task, including the start and end time, speed, amplitude and path of the saccade;

[0086] an image acquisition module for capturing video images of the patient's eye movements and the patient's facial expressions during the eye movements;

[0087] The data processing module is used to pre-process the data collected by the data acquisition module and the image acquisition module and convert the data into a unified format;

[0088] The data processing module further includes:

[0089] Capturing a video image of the patient's eyeball movement based on an image acquisition module, extracting the patient's eyeball image data, and calculating the distance between the two pupils of the patient and the shape ratio of the two eyeballs;

[0090] The eye image data of at least one patient is calculated, and based on the calculation results, the interpupillary distance is compared to determine whether it is consistent, and whether the variation range of the interpupillary distance is abnormal;

[0091] According to the judgment result, the average value of the calculated results is used as the distance between the two pupils of the patient to obtain the final pupil distance information of the patient;

[0092] The refractive power information of the patient is obtained by calculation according to the shape ratio of the two eyeballs of the patient.

[0093] In this embodiment, the motion excitation module can establish a specific visual stimulation pattern according to the diagnostic requirements of Parkinson's disease, ensuring the pertinence and effectiveness of eye movement data. The data acquisition module can record detailed information of eye movements in real time, including the start and end time, speed, amplitude and path of the saccade, providing a rich data source for subsequent analysis. The image acquisition module not only captures eye movements but also records facial expressions, providing additional visual information for diagnosis and facilitating more comprehensive symptom analysis. The data processing module converts the data into a unified format through preprocessing, facilitating subsequent feature extraction and model analysis, thereby improving data availability. Furthermore, by calculating the interpupillary distance and the shape ratio of the eyeballs, the patient's pupil distance and refractive power information can be accurately obtained. By comparing the range of variation in the interpupillary distance, abnormalities can be detected. For example, inconsistent pupil distance may indicate a neurological disease, which is extremely important for understanding the patient's visual function and the causes of eye movement abnormalities. It can more accurately diagnose Parkinson's disease and reduce misdiagnosis and missed diagnosis.

[0094] In this embodiment, the early diagnosis unit includes:

[0095] A diagnostic model building module is used to build an early diagnosis model for Parkinson's disease and train the model based on the output data of the eye movement feature extraction module and the eye gaze feature extraction module;

[0096] The eye movement abnormality feature extraction module is used to extract the asymmetric features of eye movement based on the visual function and motor ability assessment results, including: asymmetry of saccadic latency: comparing the reaction time difference between the left and right eyes in the saccadic task; asymmetry of saccadic peak velocity: comparing the maximum velocity difference between the left and right eyes during the saccadic process; asymmetry of saccadic amplitude: and the difference in movement distance of the left and right eyes during the saccadic process. Based on the asymmetric features, the degree of eye movement abnormality of the patient is assessed, specifically:

[0097] identifying saccadic events in eye movement data of a patient captured by an eye tracker based on saccadic eye movement features, and segmenting the continuous eye movement data into individual saccadic events based on the identification result;

[0098] Calculate the latency, peak velocity, and amplitude of each saccade event, and compare the differences between the left and right eyes. Calculate the mean and standard deviation of the saccade latency, peak velocity, and amplitude of the left and right eyes based on the comparison results. Obtain the asymmetry index of latency, peak velocity, and amplitude based on the calculation results.

[0099] Compare the asymmetry index of latency, peak velocity, and amplitude with the corresponding preset asymmetry index threshold to determine whether there is significant asymmetry between the left and right eyes, and comprehensively assess the degree of eye movement abnormality of the patient;

[0100] The Parkinson's disease diagnosis module is used to input the extracted eye movement abnormality features into a trained Parkinson's disease early diagnosis model for diagnosis, and output a diagnosis result including an asymmetry index and conclusion based on the evaluation results of the patient's eye movement abnormality level;

[0101] The clinical diagnosis result comparison module is used to compare the diagnostic results output by the Parkinson's disease diagnosis module with the diagnostic results of clinicians to verify the accuracy and reliability of the system. Based on the comparison results, the parameters of the Parkinson's disease early diagnosis model are adjusted to improve the performance of the diagnosis model.

[0102] In this embodiment, by combining the constructed Parkinson's disease early diagnosis model with the abnormal eye movement characteristics, the early signs of Parkinson's disease can be more accurately identified, thereby improving the accuracy of diagnosis. The abnormal eye movement feature extraction module evaluates the degree of abnormal eye movement through a quantitative method, providing doctors with objective evaluation indicators. By comparing with clinical diagnosis results, possible misdiagnosis and missed diagnosis of the system can be discovered and corrected in a timely manner, thereby improving diagnostic efficiency. Through early diagnosis, patients can receive treatment earlier, which may slow the progression of the disease and improve the quality of life.

[0103] In this embodiment, the Parkinson's disease diagnosis module further includes determining whether the patient has Parkinson's disease based on the video image of the patient's facial expression during eye movement, specifically:

[0104] obtaining a plurality of facial expression sample data of the patient based on the video image;

[0105] Extract the patient's blinking frequency, facial movement change frequency and amplitude changes from each facial expression sample data;

[0106] Identify the extracted multiple parameters, obtain identification results, and determine whether there are typical facial movement features of Parkinson's disease;

[0107] The abnormal coefficient of the patient is calculated based on the blinking frequency, facial movement change frequency and amplitude change of the patient in each facial expression sample data and the identification result of each parameter;

[0108] confirming whether the abnormal coefficient is greater than a preset coefficient; if so, obtaining an abnormal video image segment of the patient based on the video image; otherwise, preliminarily determining that the patient does not suffer from Parkinson's disease;

[0109] Extract eye feature factors from each frame of the image based on abnormal video image segments, such as wrinkles at the corners of the eyes and eyelid closure status;

[0110] Typical features of Parkinson's disease, such as mask-like face (reduced facial expression) and tremor, are screened out based on the human eye feature factors in each frame of the image;

[0111] The severity of the patient's symptoms is calculated based on the typical features of Parkinson's disease in the human eye feature factors in each frame of the image;

[0112] Confirm whether the severity of the patient's symptoms is greater than or equal to a preset threshold. If so, it is confirmed that the patient has Parkinson's disease. Otherwise, it is considered that the patient does not show typical symptoms of Parkinson's disease.

[0113] In this embodiment, the combination of eye movement and facial expression analysis can provide a more comprehensive assessment of the patient's symptoms. Combined with eye movement characteristics, it can identify signs of Parkinson's disease earlier and improve the accuracy of diagnosis. Through sophisticated video image analysis, slight facial movements and blinking abnormalities can be identified, reducing the risk of misdiagnosis and missed diagnosis that may be caused by a single indicator. By quantifying the blinking frequency, the frequency and amplitude of facial movement changes, and human eye characteristic factors, the abnormality coefficient and symptom severity are calculated, reducing the error of subjective judgment, improving the efficiency of diagnosis, helping doctors assess the severity of the disease, and providing a basis for the formulation of treatment plans. As an auxiliary tool for clinicians to diagnose Parkinson's disease, it improves the consistency and reliability of diagnosis.

[0114] Furthermore, the data acquisition unit includes:

[0115] Compensation modules for:

[0116] Collect environmental images based on the camera on the eye tracker;

[0117] Extracting brightness component information of each pixel in the environment image; determining a brightness histogram based on the brightness component information of each pixel in the environment image; determining a brightness interval based on the brightness histogram, determining a median value of the brightness interval, and counting a first number of pixels greater than the median value and a second number of pixels less than the median value; and generating and executing a lighting compensation instruction when it is determined that the second number is greater than the first number;

[0118]

[0119] in, is the grayscale value of the environment image G at (x, y) after illumination compensation; is the grayscale value of the environment image G at (x, y); is the target grayscale mean generated based on illumination compensation; The number of pixels included in the environment image;

[0120] Adjustment module for:

[0121] changing a propagation direction of the laser beam based on a first angle of rotation of the eye tracker so that the laser beam path passes through the patient's face, and adjusting a first angular resolution of capturing the patient's facial expression based on the first angle of rotation of the eye tracker;

[0122] in, is the first angular resolution; is an integer, , is the laser beam divergence angle; is the first angle between the eye tracker and the patient's face; is the maximum angle the eye tracker can rotate; is the initial angular resolution of the eye tracker;

[0123] Changing a propagation direction of the laser beam based on a second angle of rotation of the eye tracker so that the laser light path passes through the patient's eyeball, and adjusting a second angular resolution of capturing the patient's eyeball according to the second angle of rotation of the eye tracker;

[0124] in, is the second angular resolution; It is the second angle between the eye tracker and the patient's eyeball; the camera on the eye tracker collects the patient's facial expression and eye movement video data based on the first angular resolution and the second angular resolution.

[0125] The working principle of the above technical solution is as follows: The data acquisition unit is further refined to include a compensation module and an adjustment module, which are responsible for processing ambient lighting compensation and adjusting the angular resolution of the eye tracker data, respectively. In this embodiment, the compensation module uses the eye tracker's camera to capture an ambient image in the YUV color space and extracts the luminance component information, namely the Y component, for each pixel in the ambient image. A luminance histogram is a graphical representation that shows the number of pixels at different brightness levels in an image. A luminance histogram is generated by dividing the luminance values ​​into a series of intervals and counting the number of pixels within each interval. The luminance histogram is analyzed to determine the range of luminance values ​​and calculate the median of the interval, which represents the center point of the luminance distribution. A first number of pixels greater than the median and a second number of pixels less than the median are counted. If the second number is greater than the first number, it indicates that the image is generally dark, and a lighting compensation instruction is generated to increase the image brightness, thereby improving the visual quality of the image.

[0126] In this embodiment, the adjustment module adjusts the angular resolution of the eye tracker's data to accommodate different acquisition requirements. The first angular resolution for acquiring a patient's facial expression is smaller than the second angular resolution for acquiring the patient's eyeballs, requiring a higher resolution for acquiring the patient's eyeball information.

[0127] The beneficial effect of the above technical solution is that through the work of the compensation module and the adjustment module, the data acquisition unit can ensure that high-quality and high-resolution video data can be collected under different lighting conditions and collection requirements.

[0128] Furthermore, the image acquisition module includes:

[0129] The first determining module is configured to:

[0130] Performing frame processing on the video image of the patient's facial expression during eye movement to obtain a number of sub-frame images;

[0131] Performing grayscale processing on a plurality of frames of sub-images to obtain a plurality of frames of grayscale images;

[0132] Traverse each pixel on the grayscale image, add up the grayscale values ​​of each pixel, and divide the total grayscale value by the total number of pixels to obtain an average grayscale value; in the process of traversing each pixel on the grayscale image, record the maximum grayscale value and the minimum grayscale value; determine the pixel whose grayscale value is less than the average grayscale value and calculate a first grayscale sum value; determine the pixel whose grayscale value is greater than the average grayscale value and calculate a second grayscale sum value;

[0133] Calculating a feature value of the grayscale image based on the maximum grayscale value, the minimum grayscale value, the first grayscale sum value, and the second grayscale sum value;

[0134] in, is the eigenvalue of the grayscale image; is the second grayscale value; is the first grayscale value; is the maximum grayscale value; is the minimum grayscale value; comparing the characteristic value of the grayscale image with the preset characteristic threshold, screening out the grayscale images whose characteristic value is greater than the preset characteristic threshold, and determining them as the target image set;

[0135] The second determining module is configured to:

[0136] Determine a first target image and a second target image of adjacent frames in the target image set;

[0137] Acquire a first grayscale feature and a first texture feature of a first target image; acquire a first grayscale feature and a second texture feature of a second target image;

[0138] performing a first image registration on the first target image and the second target image based on the first grayscale feature and the second grayscale feature, and determining first change information of the facial expression according to a result of the first image registration;

[0139] performing a second image registration on the first target image and the second target image based on the first texture feature and the second texture feature, and determining second change information of the facial expression according to a result of the second image registration;

[0140] Determine facial expression change information based on the first change information and the second change information.

[0141] The working principle of the above technical solution: In this embodiment, a video image of a patient's facial expression during eye movement is framed, resulting in a number of sub-frame images. These sub-frames are then processed to determine the characteristic values ​​of the grayscale image. The formula takes into account the distribution range of the grayscale values ​​and the differences in the distribution of grayscale values ​​on both sides of the average grayscale value. The characteristic values ​​of the grayscale image are compared with a preset characteristic threshold, and grayscale images with characteristic values ​​greater than the preset characteristic threshold are selected and determined as the target image set. The target image set contains images that meet the image quality requirements, and images with poor image quality are eliminated.

[0142] In this embodiment, two adjacent image frames are identified and labeled as the first target image and the second target image, respectively. These two images will be used for subsequent image registration and change information extraction. Grayscale features and texture features are extracted for the first and second target images, respectively. Grayscale features typically refer to image brightness information and can be obtained by calculating the image's grayscale histogram, grayscale co-occurrence matrix, and other methods. Texture features describe the arrangement and distribution pattern of pixels in an image and can be obtained by calculating the image's local binary pattern (LBP), grayscale co-occurrence matrix statistics, Gabor filters, and other methods. The grayscale features of the first and second target images are used for the first image registration. Image registration is an image processing technique used to align two or more images acquired at different times, from different perspectives, or using different sensors so that they have consistent geometric relationships within the same coordinate system. The optimal transformation parameters (such as translation, rotation, and scaling) between the two images are found to minimize grayscale differences after alignment. Based on the results of the first image registration, initial facial expression change information, such as subtle movements of facial muscles or the degree of eye opening, can be determined. A second image registration is performed using texture features from the first and second target images. Because texture features contain more detailed image information, the second image registration may more accurately capture subtle changes in facial expression. Based on the results of the second image registration, a second facial expression change can be determined. This information may include changes in skin texture, the appearance or disappearance of wrinkles, and so on. The second determination module accurately captures and analyzes facial expression changes between adjacent frames.

[0143] The beneficial effects of the above technical solution are as follows: the work of the first determination module and the second determination module enables the image acquisition module to screen out a set of target images with significant features and high quality, and accurately determine the change information of facial expressions, thereby ensuring the accuracy of information acquisition.

[0144] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. An early diagnosis system for Parkinson's disease based on eye movement feature analysis, characterized by: include: a data acquisition unit, configured to capture the patient's eye movement data in real time based on an eye tracker, and to collect the patient's facial expression and eye movement video data in real time based on a camera on the eye tracker, and to process the acquired eye movement data and facial expression and eye movement video data; a feature extraction unit, configured to extract eye movement features related to Parkinson's disease from the processed data, including eye movement speed, movement amplitude, eye fixation stability, and eye saccadic movement features; Feature extraction unit, including: An eye movement feature extraction module is used to extract the patient's eye movement speed features and eye movement amplitude features, and to modify the eye movement speed features and eye movement amplitude features based on the patient's final pupil distance information; An eye gaze feature extraction module is used to extract the patient's eye gaze point features and eye saccadic movement features, and to evaluate the patient's visual function and motor ability based on the eye gaze point features and eye saccadic movement features based on the patient's refractive information; An early diagnosis unit is used to train and model the extracted eye movement features, establish an early diagnosis model for Parkinson's disease, input the extracted patient's eye movement features into the early diagnosis model for Parkinson's disease, obtain early diagnosis results for Parkinson's disease, and generate an early diagnosis report for Parkinson's disease; Wherein, the data acquisition unit includes: Compensation modules for: Collect environmental images based on the camera on the eye tracker; Extracting brightness component information of each pixel in the environment image; determining a brightness histogram based on the brightness component information of each pixel in the environment image; determining a brightness interval based on the brightness histogram, determining a median value of the brightness interval, and counting a first number of pixels greater than the median value and a second number of pixels less than the median value; and generating and executing a lighting compensation instruction when it is determined that the second number is greater than the first number; in, is the grayscale value of the environment image G at (x, y) after illumination compensation; is the grayscale value of the environment image G at (x, y); is the target grayscale mean generated based on illumination compensation; The number of pixels included in the environment image; Adjustment module for: changing a propagation direction of the laser beam based on a first angle of rotation of the eye tracker so that the laser beam path passes through the patient's face, and adjusting a first angular resolution of capturing the patient's facial expression based on the first angle of rotation of the eye tracker; in, is the first angular resolution; is an integer, , is the laser beam divergence angle; is the first angle between the eye tracker and the patient's face; is the maximum angle the eye tracker can rotate; is the initial angular resolution of the eye tracker; Changing a propagation direction of the laser beam based on a second angle of rotation of the eye tracker so that the laser light path passes through the patient's eyeball, and adjusting a second angular resolution of capturing the patient's eyeball according to the second angle of rotation of the eye tracker; in, is the second angular resolution; The second angle between the eye tracker and the patient's eyeball; The camera on the eye tracker collects video data of the patient's facial expressions and eye movements based on the first angular resolution and the second angular resolution.

2. The early diagnosis system for Parkinson's disease based on eye movement feature analysis according to claim 1, characterized in that: Data acquisition unit, including: The motion stimulation module is used to establish a visual stimulation pattern according to the diagnostic requirements of Parkinson's disease, generate dynamic visual stimulation according to the preset visual stimulation pattern, and display the dynamic visual stimulation on the display screen in real time to generate a saccade task; A data acquisition module is used to record the patient's eye movement data in real time based on an eye tracker when the patient performs a saccade task, including the start and end time, speed, amplitude and path of the saccade; an image acquisition module for capturing video images of the patient's eye movements and the patient's facial expressions during the eye movements; The data processing module is used to pre-process the data collected by the data acquisition module and the image acquisition module and convert the data into a unified format.

3. The early diagnosis system for Parkinson's disease based on eye movement feature analysis according to claim 2, characterized in that: The data processing module further includes: Capturing a video image of the patient's eyeball movement based on an image acquisition module, extracting the patient's eyeball image data, and calculating the distance between the two pupils of the patient and the shape ratio of the two eyeballs; The eye image data of at least one patient is calculated, and based on the calculation results, the interpupillary distance is compared to determine whether it is consistent, and whether the variation range of the interpupillary distance is abnormal; According to the judgment result, the average value of the calculated results is used as the distance between the two pupils of the patient to obtain the final pupil distance information of the patient; The refractive power information of the patient is obtained by calculation according to the shape ratio of the two eyeballs of the patient.

4. The early diagnosis system for Parkinson's disease based on eye movement feature analysis according to claim 3, characterized in that: Early Diagnosis Unit, including: A diagnostic model building module is used to build an early diagnosis model for Parkinson's disease and train the model based on the output data of the eye movement feature extraction module and the eye gaze feature extraction module; an eye movement abnormality feature extraction module, configured to extract asymmetric features of saccadic eye movements based on the visual function and motor ability assessment results, and to assess the degree of eye movement abnormality of the patient based on the asymmetric features; The Parkinson's disease diagnosis module is used to input the extracted eye movement abnormality features into a trained Parkinson's disease early diagnosis model for diagnosis, and output a diagnosis result including an asymmetry index and conclusion based on the evaluation results of the patient's eye movement abnormality level; The clinical diagnosis result comparison module is used to compare the diagnosis results output by the Parkinson's disease diagnosis module with the diagnosis results of clinicians, and adjust the parameters of the Parkinson's disease early diagnosis model based on the comparison results.

5. The early diagnosis system for Parkinson's disease based on eye movement feature analysis according to claim 4, characterized in that: The eye movement abnormality feature extraction module is specifically: identifying saccadic events in eye movement data of a patient captured by an eye tracker based on saccadic eye movement features, and segmenting the continuous eye movement data into individual saccadic events based on the identification result; Calculate the latency, peak velocity, and amplitude of each saccade event, and compare the differences between the left and right eyes. Calculate the mean and standard deviation of the saccade latency, peak velocity, and amplitude of the left and right eyes based on the comparison results. Obtain the asymmetry index of latency, peak velocity, and amplitude based on the calculation results. The asymmetry index of latency, peak velocity, and amplitude is compared with the corresponding preset asymmetry index threshold to determine whether there is significant asymmetry between the left and right eyes, and to comprehensively assess the degree of eye movement abnormality in the patient.

6. The early diagnosis system for Parkinson's disease based on eye movement feature analysis according to claim 5, characterized in that: The Parkinson's disease diagnosis module also includes determining whether the patient has Parkinson's disease based on the video image of the patient's facial expression during eye movement, specifically: obtaining a plurality of facial expression sample data of the patient based on the video image; Extract the patient's blinking frequency, facial movement change frequency and amplitude changes from each facial expression sample data; Identify the extracted multiple parameters, obtain identification results, and determine whether there are typical facial movement features of Parkinson's disease; The abnormal coefficient of the patient is calculated based on the blinking frequency, facial movement change frequency and amplitude change of the patient in each facial expression sample data and the identification result of each parameter; Confirm whether the abnormal coefficient is greater than a preset coefficient. If so, obtain an abnormal video image segment of the patient based on the video image. Otherwise, preliminarily determine that the patient does not suffer from Parkinson's disease.

7. The early diagnosis system for Parkinson's disease based on eye movement feature analysis according to claim 6, characterized in that: Obtaining an abnormal video image segment of the patient based on the video image further includes: Extracting human eye feature factors in each frame of image based on abnormal video image segments; The typical features of Parkinson's disease are screened out based on the human eye characteristic factors in each frame of the image; The severity of the patient's symptoms is calculated based on the typical features of Parkinson's disease in the human eye feature factors in each frame of the image; Confirm whether the severity of the patient's symptoms is greater than or equal to a preset threshold. If so, it is confirmed that the patient has Parkinson's disease. Otherwise, it is considered that the patient does not show typical symptoms of Parkinson's disease.

8. The early diagnosis system for Parkinson's disease based on eye movement feature analysis according to claim 2, characterized in that: The image acquisition module includes: The first determining module is configured to: Performing frame processing on the video image of the patient's facial expression during eye movement to obtain a number of sub-frame images; Performing grayscale processing on a plurality of frames of sub-images to obtain a plurality of frames of grayscale images; Traverse each pixel on the grayscale image, add up the grayscale values ​​of each pixel, and divide the total grayscale value by the total number of pixels to obtain an average grayscale value; in the process of traversing each pixel on the grayscale image, record the maximum grayscale value and the minimum grayscale value; determine the pixel whose grayscale value is less than the average grayscale value and calculate a first grayscale sum value; determine the pixel whose grayscale value is greater than the average grayscale value and calculate a second grayscale sum value; Calculating a feature value of the grayscale image based on the maximum grayscale value, the minimum grayscale value, the first grayscale sum value, and the second grayscale sum value; in, is the eigenvalue of the grayscale image; is the second grayscale value; is the first grayscale value; is the maximum grayscale value; is the minimum gray value; Compare the characteristic value of the grayscale image with a preset characteristic threshold, filter out the grayscale images whose characteristic value is greater than the preset characteristic threshold, and determine them as the target image set; The second determining module is configured to: Determine a first target image and a second target image of adjacent frames in the target image set; Acquire a first grayscale feature and a first texture feature of a first target image; acquire a first grayscale feature and a second texture feature of a second target image; performing a first image registration on the first target image and the second target image based on the first grayscale feature and the second grayscale feature, and determining first change information of the facial expression according to a result of the first image registration; performing a second image registration on the first target image and the second target image based on the first texture feature and the second texture feature, and determining second change information of the facial expression according to a result of the second image registration; Determine facial expression change information based on the first change information and the second change information.

Images