A system and method for monitoring the progression of thyroid-related eye disease

Abstract

The present application relates to the field of image analysis technology, and in particular to a system for monitoring the progression of thyroid-related eye diseases. The progression monitoring method is applied to an eye detector, and the method includes: obtaining an eye monitoring video captured by a camera device, analyzing the eye monitoring video, and determining eye features; analyzing the eye features to determine the degree of eyelid opening and closing and eyeball movement; determining pupil changes based on eyeball movement; determining the current state of the eye disease based on the degree of eyelid opening and closing, eyeball movement, and pupil changes; obtaining and analyzing historical eye disease diagnosis and treatment records to obtain the historical state of the eye disease; comparing the current state of the eye disease with the historical state of the eye disease to determine whether the thyroid-related eye disease has improved.

Description

Technical Field

[0001] The present application relates to the field of image analysis technology, and in particular to a system and method for monitoring the progression of thyroid-related eye diseases. Background Art

[0002] Thyroid-associated eye disease is a specific autoimmune disease that affects the thyroid gland and orbital organs at the same time. It is one of the most common orbital diseases in adults.

[0003] Currently, the treatment of thyroid-related eye diseases is mostly through a comprehensive analysis of face-to-face consultations combined with CT angiography scans to determine the severity of the patient's thyroid-related eye disease. Subsequent confirmation of the progress of treatment for thyroid-related eye diseases also requires going to the hospital for evaluation by a doctor. This process is not only very troublesome for patients, but also for doctors. Since there is a certain time interval between the initial diagnosis and the re-examination, if there are any problems in the middle that cause the thyroid-related eye disease to become more serious, this is unknown. Therefore, the diagnosis after the re-examination will be the same as the initial diagnosis, which is time-consuming and laborious, and the cause of the disease cannot be found, delaying the patient's condition and endangering the patient's health. Summary of the Invention

[0004] The present application provides a system and method for monitoring the progression of thyroid-related eye diseases to solve the above-mentioned problems.

[0005] In a first aspect, the present application provides a method for monitoring the progression of thyroid-related eye disease, wherein the method is applied to an eye detector, wherein the eye detector includes a camera device and a data processing chip, and the method is applied to the data processing chip; the method comprises:

[0006] Obtaining an eye monitoring video captured by the camera device, analyzing the eye monitoring video, and determining eye features;

[0007] Analyzing the eye characteristics to determine the degree of eyelid opening and closing and eye movement;

[0008] determining pupil changes according to the eye movement;

[0009] Determining the current eye disease state according to the eyelid opening and closing degree, the eyeball movement, and the pupil change;

[0010] Obtain and analyze historical eye disease diagnosis and treatment records to obtain historical eye disease status; compare the current eye disease status with the historical eye disease status to determine whether the thyroid-related eye disease has improved.

[0011] Through this solution, eye monitoring videos captured by the camera device are acquired in real time, enabling real-time capture of changes in eye status. Video analysis and image processing technologies provide objective eye feature data, reducing the subjectivity of human judgment. Advanced image processing algorithms are used to accurately measure the degree of eyelid opening and closing, eye movement, and pupil changes, improving the accuracy and reliability of diagnosis. Combining multiple eye features for comprehensive judgment avoids the limitations of a single indicator and provides comprehensive information for the assessment of eye disease status. Historical eye disease diagnosis and treatment records are obtained and analyzed to comprehensively track changes in the patient's condition. By comparing the current eye disease status with the historical eye disease status, the treatment effect can be intuitively evaluated, providing a basis for adjusting the treatment plan. This avoids the situation where doctors cannot intuitively judge the patient's condition during follow-up visits due to long time intervals, resulting in the disease not being cured in time.

[0012] Optionally, obtaining the eye monitoring video captured by the camera device includes:

[0013] Acquire and analyze a starting eye image, and determine whether eye deviation exists based on the image analysis result;

[0014] If it is determined that eye deviation exists, the eye deviation angle is determined based on the image analysis results;

[0015] The eye difference is determined according to the eye deviation angle and the historical eye disease diagnosis and treatment records, and the image capture method is adjusted according to the eye difference, and the eye monitoring video is obtained according to the adjusted image capture method.

[0016] This solution uses image analysis technology to analyze the initial eye image to determine whether there is eye deviation, preliminarily determine the eye position and the wearing position of the eye detector, and determine the eye deviation angle. Then, based on the eye deviation angle and historical eye disease diagnosis and treatment records, the eye position image is differentiated to prepare for subsequent image adjustments. By determining the image capture method and adjusting the shooting area, accurate capture can be achieved even when the patient's wearing is not standard, reducing video errors and improving the accuracy of subsequent eye disease status judgments.

[0017] Optionally, the eye detector includes a camera device; acquiring and analyzing the initial eye image, and determining whether eye deviation exists based on the image analysis result, includes:

[0018] monitoring the displacement change of the eye detector in real time, and determining whether the spatial position of the eye detector has changed based on the displacement change;

[0019] If it is determined that there is a spatial position change, determining a horizontal position change amplitude based on the spatial position change;

[0020] determining whether to activate the camera device according to the horizontal position change amplitude;

[0021] If it is determined to start the camera device, acquiring and screening the image captured by the camera device to obtain the initial eye image;

[0022] Analyzing the initial eye image, and extracting eye features based on the image analysis result;

[0023] A structure boundary is determined based on the eye features, and the eye features within each structure are analyzed based on the structure boundaries to determine whether eye offset exists.

[0024] This solution, integrating high-precision sensors and real-time data processing technology, monitors the displacement of the eye detector in real time. When the spatial position of the eye detector changes, the magnitude of the change determines whether to activate the camera. This automated camera activation eliminates the need for manual intervention. The camera captures images that are filtered to ensure a clear and accurate initial eye image. Advanced image recognition technology is then used to extract eye features, further improving analysis accuracy. After extracting the eye features, the structural boundaries of the eye are determined based on these features. This structured analysis facilitates more precise localization and analysis of eye deviation.

[0025] Optionally, analyzing eye features within each structure according to the structure boundary to determine whether eye offset exists includes:

[0026] determining an eyelid region based on the structure boundaries and eye features within each structure;

[0027] analyzing eye features of the eyelid region to determine an eyelid shadow area;

[0028] determining the eyelid shadow area according to the eyelid shadow region;

[0029] Obtaining the current lighting conditions and the spatial position of the camera device;

[0030] determining a desired eyelid shadow area according to the current lighting conditions and the spatial position;

[0031] Comparing the eyelid shadow area with the expected eyelid shadow area to determine whether the eyelid shadow area is larger than the expected eyelid shadow area;

[0032] If the eyelid shadow area is greater than the expected eyelid shadow area, it is determined that eye deviation exists.

[0033] This solution meticulously analyzes eye features within each structure and precisely locates the eyelid region, helping to more accurately capture changes in eye features. This solution not only focuses on the eye features themselves but also takes into account the current lighting conditions and the spatial position of the camera. By incorporating these environmental factors into the analysis, a more comprehensive assessment of the expected eyelid shadow area is achieved. By comparing the actual eyelid shadow area with the expected eyelid shadow area, an intelligent determination of eye deviation is made. This automated judgment reduces the errors and uncertainties caused by human factors.

[0034] Optionally, analyzing the eye monitoring video to determine eye features includes:

[0035] analyzing the eye monitoring video to determine changes in light and dark;

[0036] Determining a current detection mode according to the light and dark changes;

[0037] According to the current detection mode, the eye monitoring video is analyzed frame by frame to determine eye features.

[0038] This solution analyzes eye monitoring video and determines detection patterns based on changes in brightness and darkness. Through refined frame-by-frame analysis and dynamically adjusted detection patterns, it can more effectively identify eye features, reducing false positives and missed positives. This helps improve overall performance and user experience.

[0039] Optionally, analyzing the eye features to determine the degree of eyelid opening and closing and eye movement includes:

[0040] Analyzing the eye features to determine the eyelid contour and eyeball area;

[0041] determining the relative position between the eyelid contour and the eyeball area according to the feature vector of the eye feature;

[0042] determining an eyelid opening / closing ratio according to the relative position, and determining an eyelid opening / closing degree according to the eyelid opening / closing ratio;

[0043] Determining the pupil position in each frame of video according to the eye features;

[0044] According to the pupil position in each frame of video, the pupil change speed, pupil change direction and pupil change acceleration are determined;

[0045] The eye movement condition is determined according to the pupil change speed, the pupil change direction and the pupil change acceleration.

[0046] This solution calculates the relative position between the eyelid contour and the eyeball area, accurately determining the eyelid opening / closing ratio and, therefore, the degree of eyelid opening / closing. It also tracks the pupil position in real time throughout each video frame, making it possible to calculate the pupil's speed, direction, and acceleration. By comprehensively considering the pupil's speed, direction, and acceleration, a comprehensive assessment of eye movement can be achieved, resulting in more accurate eye movement data and facilitating subsequent detection and diagnosis of eye diseases in patients.

[0047] Optionally, determining pupil changes based on the eye movement includes:

[0048] Based on the eye movement, real-time acquisition of environmental changes;

[0049] determining a pupil inspection mode according to the environmental changes;

[0050] determining the real-time position of the pupil according to the eye movement;

[0051] Determining a real-time pupil diameter based on the real-time pupil position and the eye features;

[0052] The pupil change is determined according to the pupil inspection mode and the real-time pupil diameter.

[0053] This solution uses real-time monitoring of eye movements to quickly capture the ambient light as the eyes zoom in and out. Based on these changes in the surrounding environment, the pupil examination mode is determined. This allows analysis of pupil changes to be closely linked to different examination modes, facilitating subsequent analysis of the patient's condition. Furthermore, it better meets the patient's eye examination needs. Changes in pupil diameter can directly reflect the pupil's response to different environmental stimuli, helping to assess the patient's visual accommodation ability and thus making it easier to analyze the patient's condition.

[0054] Optionally, the eye movement condition is determined according to the pupil change speed, the pupil change direction, and the pupil change acceleration, with reference to the following formula:

[0055] ;

[0056] in, represents the eye movement index; represents the pupil change speed; A weight coefficient representing the pupil change speed; represents the average value of the pupil change speed within a preset detection period; represents the standard deviation of the pupil change speed; A weight coefficient representing the pupil change direction; represents the quantified direction of pupil change; A weight coefficient representing the pupil change acceleration; represents the pupil change acceleration; represents the average acceleration of the pupil change acceleration within a preset detection period; represents the standard deviation of the pupil change acceleration;

[0057] The eye movement condition is determined according to the eye movement index.

[0058] This solution considers pupil change speed, pupil change direction, and pupil change acceleration, and designs a formula to calculate the eye zoom index, which is then used to reflect eye movement. This allows for a more comprehensive and accurate assessment of eye movement. Furthermore, the designed formula can digitize complex content, making it easier to reflect eye movement.

[0059] Optionally, determining the current eye disease state based on the eyelid opening and closing degree, the eyeball movement, and the pupil change includes:

[0060] Determining the last inspection data according to the current inspection mode;

[0061] Determining the last eyelid opening and closing degree, the last eyeball zooming degree, and the last pupil change according to the last examination data;

[0062] Determining an eye change trend based on the eyelid opening and closing degree, the eyeball movement, the pupil change, the last eyelid opening and closing degree, the last eyeball zooming degree, and the last pupil change;

[0063] The current state of the eye disease is determined based on the eye change trend.

[0064] This solution integrates data from multiple dimensions, including eyelid opening and closing, eye movement, and pupil changes, providing a solid foundation for comprehensive eye assessment. Comparing current test data with the most recent test accurately captures changing trends in eye condition. Analyzing these trends can determine the current state of eye disease and provide a basis for subsequent assessment of improvement.

[0065] In a second aspect, the present application provides a system for monitoring the progression of thyroid-related eye diseases, the system comprising:

[0066] a feature determination module, configured to acquire an eye monitoring video captured by a camera device, analyze the eye monitoring video, and determine eye features;

[0067] A feature analysis module, configured to analyze the eye features and determine the degree of eyelid opening and closing and eye movement;

[0068] A pupil analysis module, configured to determine pupil changes based on the eye movement;

[0069] A state analysis module determines the current state of eye disease based on the degree of eyelid opening and closing, the eyeball movement, and the pupil changes;

[0070] The symptom analysis module is used to obtain and analyze historical eye disease diagnosis and treatment records to obtain historical eye disease status; compare the current eye disease status with the historical eye disease status to determine whether the thyroid-related eye disease has improved.

[0071] Optionally, the feature determination module is specifically configured to:

[0072] Acquire and analyze a starting eye image, and determine whether eye deviation exists based on the image analysis result;

[0073] If it is determined that eye deviation exists, the eye deviation angle is determined based on the image analysis results;

[0074] The eye difference is determined according to the eye deviation angle and the historical eye disease diagnosis and treatment records, and the image capture method is adjusted according to the eye difference, and the eye monitoring video is obtained according to the adjusted image capture method.

[0075] Optionally, the eye detector includes a camera device; and the feature determination module is specifically configured to:

[0076] monitoring the displacement change of the eye detector in real time, and determining whether the spatial position of the eye detector has changed based on the displacement change;

[0077] If it is determined that there is a spatial position change, determining a horizontal position change amplitude based on the spatial position change;

[0078] determining whether to activate the camera device according to the horizontal position change amplitude;

[0079] If it is determined to start the camera device, acquiring and screening the image captured by the camera device to obtain the initial eye image;

[0080] Analyzing the initial eye image, and extracting eye features based on the image analysis result;

[0081] A structure boundary is determined based on the eye features, and the eye features within each structure are analyzed based on the structure boundaries to determine whether eye offset exists.

[0082] Optionally, the feature determination module is specifically configured to:

[0083] determining an eyelid region based on the structure boundaries and eye features within each structure;

[0084] analyzing eye features of the eyelid region to determine an eyelid shadow area;

[0085] determining the eyelid shadow area according to the eyelid shadow region;

[0086] Obtaining the current lighting conditions and the spatial position of the camera device;

[0087] determining a desired eyelid shadow area according to the current lighting conditions and the spatial position;

[0088] Comparing the eyelid shadow area with the expected eyelid shadow area to determine whether the eyelid shadow area is larger than the expected eyelid shadow area;

[0089] If the eyelid shadow area is greater than the expected eyelid shadow area, it is determined that eye deviation exists.

[0090] Optionally, the feature determination module is specifically configured to:

[0091] analyzing the eye monitoring video to determine changes in light and dark;

[0092] Determining a current detection mode according to the light and dark changes;

[0093] According to the current detection mode, the eye monitoring video is analyzed frame by frame to determine eye features.

[0094] Optionally, the feature analysis module is specifically used to:

[0095] Analyzing the eye features to determine the eyelid contour and eyeball area;

[0096] determining the relative position between the eyelid contour and the eyeball area according to the feature vector of the eye feature;

[0097] determining an eyelid opening / closing ratio according to the relative position, and determining an eyelid opening / closing degree according to the eyelid opening / closing ratio;

[0098] Determining the pupil position in each frame of video according to the eye features;

[0099] According to the pupil position in each frame of video, the pupil change speed, pupil change direction and pupil change acceleration are determined;

[0100] The eye movement condition is determined according to the pupil change speed, the pupil change direction and the pupil change acceleration.

[0101] Optionally, the pupil analysis module is specifically used to:

[0102] Based on the eye movement, real-time acquisition of environmental changes;

[0103] determining a pupil inspection mode according to the environmental changes;

[0104] determining the real-time position of the pupil according to the eye movement;

[0105] Determining a real-time pupil diameter based on the real-time pupil position and the eye features;

[0106] The pupil change is determined according to the pupil inspection mode and the real-time pupil diameter.

[0107] Optionally, the feature analysis module is specifically used to:

[0108] ;

[0109] in, represents the eye movement index; represents the pupil change speed; A weight coefficient representing the pupil change speed; represents the average value of the pupil change speed within a preset detection period; represents the standard deviation of the pupil change speed; A weight coefficient representing the pupil change direction; represents the quantified direction of pupil change; A weight coefficient representing the pupil change acceleration; represents the pupil change acceleration; represents the average acceleration of the pupil change acceleration within a preset detection period; represents the standard deviation of the pupil change acceleration;

[0110] The eye movement condition is determined according to the eye movement index.

[0111] Optionally, when determining the current eye disease state based on the eyelid opening and closing degree, the eyeball movement, and the pupil change, the state analysis module is specifically used to:

[0112] Determining the last inspection data according to the current inspection mode;

[0113] Determining the last eyelid opening and closing degree, the last eyeball zooming degree, and the last pupil change according to the last examination data;

[0114] Determining an eye change trend based on the eyelid opening and closing degree, the eyeball movement, the pupil change, the last eyelid opening and closing degree, the last eyeball zooming degree, and the last pupil change;

[0115] The current state of the eye disease is determined based on the eye change trend. BRIEF DESCRIPTION OF THE DRAWINGS

[0116] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0117] Figure 1 A schematic diagram of an application scenario provided in one embodiment of the present application;

[0118] Figure 2 This is a flow chart of a method for monitoring the progression of thyroid-related eye disease provided in one embodiment of the present application;

[0119] Figure 3 This is a schematic structural diagram of a system for monitoring the progression of thyroid-related eye diseases provided in one embodiment of the present application. DETAILED DESCRIPTION

[0120] To make the purpose, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0121] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0122] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0123] If you want to determine the progress of treatment for thyroid-related eye disease in the future, you also need to go to the hospital for evaluation by a doctor. This process is not only very troublesome for patients, but also for doctors. Since there is a certain time interval between the initial diagnosis and the re-examination, if there is any problem in the middle that causes the thyroid-related eye disease to become more serious, it is impossible to know. Therefore, the diagnosis after the re-examination will be the same as the initial diagnosis, which is time-consuming and laborious, and the cause of the disease cannot be found, which delays the patient's condition and endangers the patient's health.

[0124] Based on this, the present application provides a system and method for monitoring the progression of thyroid-related eye diseases, which acquires eye monitoring videos taken by a camera in real time and realizes real-time capture of changes in eye status. Video analysis and image processing technology provide objective eye feature data, reducing the subjectivity of human judgment. Advanced image processing algorithms are used to accurately measure the degree of eyelid opening and closing, eye movement, and pupil changes, thereby improving the accuracy and reliability of diagnosis. Combining multiple eye features for comprehensive judgment avoids the limitations of a single indicator and provides comprehensive information for the assessment of eye disease status. Historical eye disease diagnosis and treatment records are obtained and analyzed to comprehensively track changes in the patient's condition. By comparing the current eye disease status with the historical eye disease status, the treatment effect can be intuitively evaluated, providing a basis for adjusting the treatment plan. This avoids the situation where the doctor cannot intuitively judge the patient's condition during follow-up visits due to a long time interval, resulting in the disease not being cured in time.

[0125] Figure 1 This is a schematic diagram of an application scenario provided by this application. When it is necessary to monitor the treatment progress of thyroid-related eye diseases, the method provided by this application can be applied.

[0126] Specifically, the method provided in this application is applied to any eye detector, which interacts with the attending physician's server. The eye detector is equipped with a camera and a data processing chip. The eye monitoring video captured by the camera is obtained and transmitted to the data processing chip for analysis. The eye features are determined and analyzed, the degree of eyelid opening and closing and the eye movement are determined, and then the eye movement is analyzed to determine the pupil changes. The current eye disease status is determined by combining the eyelid opening and closing, eye movement, and pupil changes. The patient's historical eye disease diagnosis and treatment records in the attending physician's server are retrieved and analyzed to obtain the historical eye disease status. The current eye disease status is compared with the historical eye disease status to determine whether there is improvement in thyroid-related eye disease. Video analysis and image processing technology provide objective eye feature data, reducing the subjectivity of human judgment. Combining multiple eye features for comprehensive judgment avoids the limitations of a single indicator and provides comprehensive information for the assessment of eye disease status.

[0127] For specific implementation methods, please refer to the following embodiments.

[0128] Figure 2 This is a flow chart of a method for monitoring the progression of thyroid-related eye disease provided in one embodiment of the present application. The method of this embodiment can be applied to the eye detector in the above scenario. Figure 2 As shown, the method includes:

[0129] S201: Obtain an eye monitoring video captured by a camera device, analyze the eye monitoring video, and determine eye features.

[0130] The eye monitor can be understood as an instrument worn around the eye area. It has a physical start button. Patients using the eye monitor for eye testing can choose when to start the device, such as after the device is worn. When the physical button is pressed to send a start signal, the camera automatically turns on to shoot. All videos generated during the shooting process can be filtered to eliminate useless frames, such as images of non-eye areas taken by patients who started the device before the device was worn. After the screening is completed, the most popular eye monitoring video is obtained. Image analysis technology is used to analyze the eye monitoring video to determine the eye area and extract eye features.

[0131] In some implementations, a strain gauge sensor and a gyroscope can be installed in the eye monitor's strap. The strain gauge senses the stretch or compression of the strap, thereby determining its tightness. Generally, when a patient transitions from wearing the device to wearing it, the strap transitions from its original state to a stretched state. At this point, the strain gauge sensor receives data indicating the strap has stretched, indicating that the patient has put the device on. At this point, the gyroscope in the eye monitor detects whether the device is stable, meaning it has transitioned from a shaky state to a stationary state, indicating the transition from being picked up to being put on. If the device is stable, a start signal can be sent to the camera for video capture.

[0132] S202: Analyze eye features to determine the degree of eyelid opening and closing and eyeball movement.

[0133] The eye features obtained above are analyzed to determine the eyelid and eyeball regions. The eye features are then segmented by frame. By analyzing pixel changes in the eye features for each frame, changes in the eyelid region are determined. The distance from the eyelid edge to the center of the eyeball in each frame is calculated to determine the degree of eyelid opening. In specific implementations, metrics such as the eye aspect ratio can also be used to determine the degree of eyelid opening.

[0134] Similarly, after distinguishing the eye features in each frame in the above manner, the eye movement is determined by tracking the position and range of the pixel points in the eye area of ​​each frame.

[0135] S203: Determine pupil changes based on eye movement.

[0136] After obtaining the eye movement situation, the eye area in each frame is further distinguished by feature pixels to determine the eye pixels and pupil pixels. The size of the exit pupil is determined through the pupil pixels. Then, the changes in the size of each frame are analyzed frame by frame to determine the changes in the exit pupil.

[0137] S204: Determine the current eye disease status based on the degree of eyelid opening and closing, eyeball movement, and pupil changes.

[0138] A database is pre-set in the data processing chip of the eye detector, which is used to store the normal eye conditions corresponding to different age groups and different eye features, as well as the basic information of the patient using the eye detector, such as age, gender, etc. After obtaining the eyelid opening and closing degree, eye movement, and pupil changes in the above manner, first, according to the patient's basic information, the corresponding age group and the patient's eye features, such as single eyelids, eye distance, eye length, etc. are determined. According to these features, the corresponding normal eye conditions are retrieved from the preset database, and then the corresponding eyelid opening and closing degree, eye movement, and pupil changes under the normal eye state are compared one by one with the current eyelid opening and closing degree, eye movement, and pupil changes, so as to determine whether there is an eye disease and the current eye disease status.

[0139] In a specific implementation, the preset database may also store eye features of several known eye diseases at different degrees. When the above steps determine that there is a difference from the normal eye state, the current eyelid opening and closing degree, eye movement, and pupil changes may be used to select data that matches the state from the eye features of known eye diseases at different degrees, and the eye disease and degree of disease corresponding to this state may be used as the patient's current eye disease state.

[0140] S205. Obtain and analyze historical eye disease diagnosis and treatment records to obtain historical eye disease status; compare the current eye disease status with the historical eye disease status to determine whether there is improvement in thyroid-related eye disease.

[0141] The patient's historical eye disease diagnosis and treatment records can be retrieved through the server of the attending physician of China Unicom. In a specific implementation, when the attending physician diagnoses the patient and confirms that the patient needs to use an eye monitor for continuous eye disease progression monitoring, the diagnosis records can be directly transmitted to the corresponding eye monitor. These diagnosis records can be stored as historical eye disease diagnosis and treatment records in the aforementioned preset database, and the historical eye disease diagnosis and treatment records can then be directly retrieved from the preset database.

[0142] Natural language processing is performed on the historical eye disease diagnosis and treatment records to determine the historical eye disease status described in the records. The historical eye disease status is compared with the current eye disease status to determine whether it has improved. For example, a wider range of eyelid opening and closing indicates improvement.

[0143] Through the solution provided by this embodiment, the eye monitoring video captured by the camera device is obtained in real time, and the real-time capture of changes in eye status is achieved. Video analysis and image processing technology provide objective eye feature data, reducing the subjectivity of human judgment. Advanced image processing algorithms are used to accurately measure the degree of eyelid opening and closing, eye movement and pupil changes, thereby improving the accuracy and reliability of diagnosis. Combining multiple eye features for comprehensive judgment avoids the limitations of a single indicator and provides comprehensive information for the assessment of eye disease status. Historical eye disease diagnosis and treatment records are obtained and analyzed to comprehensively track changes in the patient's condition. By comparing the current eye disease status with the historical eye disease status, the treatment effect can be intuitively evaluated, providing a basis for adjusting the treatment plan. This avoids the situation where the doctor cannot intuitively judge the patient's condition during follow-up visits due to a long time interval, resulting in the disease not being cured in time.

[0144] In some embodiments, an initial eye image is acquired and analyzed, and based on the image analysis results, it is determined whether eye deviation exists; if it is determined that eye deviation exists, the eye deviation angle is determined based on the image analysis results; based on the eye deviation angle and historical eye disease diagnosis and treatment records, eye differences are determined, and based on the eye differences, the image capture method is adjusted, and based on the adjusted image capture method, the eye monitoring video taken by the camera device is acquired.

[0145] The initial eye image can be considered as the first frame captured after the camera device is started.

[0146] The image capture method can be considered to utilize the self-correction image technology within the device to adjust the layout of the offset image so that the video capture can be correct without adjusting the eye detector.

[0147] Specifically, after starting the camera device in the above manner, the camera device can be set to take an image first, that is, the starting eye image, which is used to analyze the starting eye image to determine whether there is a positional offset when the patient wears the device. At this time, the position of the eye in the image corresponding to a wear without positional offset can be determined based on the historical wearing records, and then, if the eye is not completely in this position without correction, it can be considered that there is an eye offset. At the same time, when it is determined that there is an offset, a plane rectangular coordinate system is established based on the relationship between the two corresponding positions, and the angle between the two is determined to obtain the eye offset angle. In a specific implementation method, the position of the eye in the image corresponding to a wear without positional offset can be obtained by the attending physician wearing the device for the first time before the device is worn. This position can be stored in the historical eye disease diagnosis and treatment records.

[0148] When there is eye offset, the eye position in the initial eye image can be compared with the corresponding eye position in the image when the device is worn without position offset, so as to determine the eye difference, and perform automatic correction based on this eye difference. After correction, it is determined that the eye position in the initial eye image is consistent with the corresponding eye position in the image when the device is worn without position offset, and then the eye monitoring video can be shot and acquired.

[0149] In a specific implementation, if it is not the first time for the patient to wear the eye detector, that is, the patient has used it multiple times and has usage data, the eye difference can be determined based on the angle when it was last worn.

[0150] The solution provided in this embodiment uses image analysis technology to analyze the initial eye image to determine whether there is eye deviation, preliminarily determine the eye position and the wearing position of the eye detector, and determine the eye deviation angle. Then, based on the eye deviation angle and historical eye disease diagnosis and treatment records, the image of the eye position is differentiated to prepare for subsequent image adjustments. By determining the image capture method and adjusting the shooting area, accurate capture can be achieved even when the patient's wearing is not standard, reducing video errors and improving the accuracy of subsequent eye disease status judgment.

[0151] In some embodiments, the displacement changes of the eye detector are monitored in real time, and based on the displacement changes, it is determined whether there is a spatial position change of the eye detector; if it is determined that there is a spatial position change, the amplitude of the horizontal position change is determined based on the spatial position change; based on the amplitude of the horizontal position change, it is determined whether to start the camera device; if it is determined that the camera device is started, the shooting picture of the camera device is acquired and filtered to obtain an initial eye image; the initial eye image is analyzed, and eye features are extracted based on the image analysis results; based on the eye features, the structural boundaries are determined, and based on the structural boundaries, the eye features within each structure are analyzed to determine whether there is eye offset.

[0152] A high-precision gyroscope can be integrated into the eye detector to analyze the position changes of the eye detector in real time, obtain the displacement changes of the eye detector, and thus determine whether there is a spatial position change of the eye detector. At this time, someone may want to pick it up for observation rather than for an eye examination. Therefore, it is necessary to determine the amplitude of the horizontal position change through the spatial position change. For example, a spatial rectangular coordinate system is established based on the position of the eye detector before the change, and then the change of the spatial coordinates is determined based on the continuous spatial position change, so that the final horizontal position change amplitude is obtained based on the change in the spatial coordinates.

[0153] When the horizontal position reaches a certain level of change, further analysis can be performed to determine whether there is any fluctuation or other positional changes. If the horizontal position rises linearly and then stabilizes at a certain point, it can be considered that an eye examination may be necessary. In this case, the camera can be automatically activated.

[0154] After the camera device is started, it can continuously capture images. At this time, the captured images can be filtered to obtain one or more complete eye images related to the eyes, and these complete eye images can be further filtered to obtain the complete eye image with the highest clarity as the starting eye image.

[0155] After obtaining the initial eye image, image analysis technology is used to extract eye features. Based on the spatial distribution and morphological characteristics of these features, the structural boundaries of the eye are determined, and a more detailed eye feature analysis is performed to determine whether there is eye deviation.

[0156] The solution provided by this embodiment integrates high-precision sensors and real-time data processing technology to monitor the displacement changes of the eye detector in real time. When the spatial position of the eye detector changes, the magnitude of the spatial position change immediately determines whether to activate the camera device for recording, thus achieving automated camera activation without manual intervention. The images captured by the camera device are screened to ensure that a clear and accurate initial eye image is obtained. Subsequently, advanced image recognition technology is used to extract eye features, further improving the accuracy of the analysis. After extracting the eye features, the structural boundaries of the eye are determined based on these features. Structured analysis helps to more accurately locate and analyze eye displacement phenomena.

[0157] In some embodiments, the eyelid region is determined based on the structural boundaries and the eye features within each structure; the eye features of the eyelid region are analyzed to determine the eyelid shadow region; the eyelid shadow area is determined based on the eyelid shadow region; the current lighting conditions and the spatial position of the camera device are obtained; the expected eyelid shadow area is determined based on the current lighting conditions and the spatial position; the eyelid shadow area is compared with the expected eyelid shadow area to determine whether the eyelid shadow area is larger than the expected eyelid shadow area; if the eyelid shadow area is larger than the expected eyelid shadow area, it is determined that there is an eye offset.

[0158] The expected eyelid shadow area can be the area of ​​the eyelid shadow when the patient is undergoing an eye examination using the above-mentioned eye detector and is wearing the device correctly and under consistent environmental conditions. It can be determined by the image obtained by the attending physician when wearing the device in the above-mentioned embodiment.

[0159] Using the structure boundaries obtained in the above embodiment and the eye features within each structure, the structure is determined, and the portion of each structure that belongs to the eyelid region is determined. The eyelid region's eye features, including the position and shape of the eyelid, are analyzed to calculate the shadow area of ​​the eyelid region using a pixel counting method.

[0160] By integrating a light sensor into the eye monitor, the current lighting conditions at the time of the initial eye image capture are determined. This is then combined with the spatial position of the camera to determine eyelid occlusion and the expected eyelid shadow area under normal eye wear when the initial eye image is captured. This can be predicted using deep learning, combined with the patient's initial normal eye wear.

[0161] In a specific implementation, image processing technology may also be used to determine the light intensity and light direction in the initial eye image.

[0162] After the expected eyelid shadow area is determined, it is compared with the actual eyelid shadow area. If the eyelid shadow area is larger than the expected eyelid shadow area, it is determined that eye deviation exists.

[0163] In a specific implementation, an area threshold may be set. If the eyelid shadow area is larger than the expected eyelid shadow area, and the difference between the two is larger than the area threshold, it may be considered that eye deviation exists.

[0164] The solution provided in this embodiment meticulously analyzes the eye features within each structure, precisely locating the eyelid region and helping to more accurately capture changes in eye features. This solution not only focuses on the eye features themselves but also takes into account the current lighting conditions and the spatial position of the camera. By incorporating these environmental factors into the analysis, a more comprehensive assessment of the expected eyelid shadow area is achieved. By comparing the actual eyelid shadow area with the expected eyelid shadow area, an intelligent determination is made as to whether the eye is offset. This automated determination reduces the errors and uncertainties caused by human factors.

[0165] In some embodiments, the eye monitoring video is analyzed to determine changes in light and dark; based on the changes in light and dark, the current detection mode is determined; based on the current detection mode, the eye monitoring video is analyzed frame by frame to determine eye features.

[0166] The current test mode can be the eye test mode the patient is currently undergoing. To achieve a more comprehensive test, several test modes can be pre-set. Different test modes have different characteristics. For example, when performing pupil testing, there will be obvious alternations between light and dark.

[0167] Specifically, after obtaining the eye monitoring video, each frame of the eye monitoring video is calculated to determine the global average brightness or histogram distribution of each frame to evaluate the overall brightness and darkness changes. According to the overall brightness range of the video, a threshold for brightness and darkness changes is set. When the brightness difference between adjacent frames exceeds the threshold, it is considered that a significant brightness and darkness change has occurred. Based on the possible sensitive changes of several pre-set detection modes and the brightness and darkness changes in each current frame, the current detection mode is determined. After determining the current detection mode, a frame-by-frame analysis is performed based on the characteristics of the current detection mode to determine the characteristics of the eye under the current detection mode.

[0168] The solution provided in this embodiment analyzes eye monitoring video and determines the detection mode based on changes in brightness and darkness. Through refined frame-by-frame analysis and dynamically adjusted detection modes, eye features can be more effectively identified, reducing false positives and missed negatives. This helps improve overall performance and user experience.

[0169] In some embodiments, eye features are analyzed to determine the eyelid contour and eyeball area; based on the feature vector of the eye features, the relative position between the eyelid contour and the eyeball area is determined; based on the relative position, the opening and closing ratio of the eyelid is determined, and based on the opening and closing ratio, the degree of eyelid opening and closing is determined; based on the eye features, the pupil position in each frame of video is determined; based on the pupil position in each frame of video, the pupil change speed, pupil change direction and pupil change acceleration are determined; based on the pupil change speed, pupil change direction and pupil change acceleration, the eyeball movement is determined.

[0170] The eyelid opening and closing ratio can be understood as the ratio of the eyelid open part to the fully open state when the eyes are open.

[0171] The eyelid opening and closing degree can be understood as the current eyelid opening and closing ratio compared to the eyelid opening and closing degree of the patient when the eye is in a normal eye state.

[0172] Specifically, the eye features obtained in the above embodiment are first processed to reduce errors. An edge detection algorithm is used to identify the area excluding the eyelids and clearly define the eyelid contours. Then, all eye features are classified using color segmentation. Texture analysis is performed on the classified eye features to determine relevant features of the eyeball. Based on the color and texture of these features, the area excluding the eyeball is determined.

[0173] Based on the eyelid contour and eyeball area determined above, the eye features at the corresponding positions are converted into feature vectors, the feature vectors of the eyelid contour and the feature vectors of the eyeball area are compared, and the relative position relationship between the two, such as distance, angle, etc., is calculated.

[0174] To better judge the degree of eyelid opening and closing, an opening and closing ratio threshold can be set in advance according to the patient's eye condition. Multiple thresholds can be set to reflect the degree of eyelid opening and closing under different eyelid opening and closing ratios, such as fully open, half open, closed, etc.

[0175] According to the eye features corresponding to the eyeball area, using the grayscale, shape and other features of the pupil, machine learning is used to locate the position of the pupil, or according to the changes in the feature vector corresponding to the eye features in each frame of video, the pupil position in each frame of video is determined. Based on the pupil position in each frame of video and combined with the change speed of each frame, the pupil change speed, pupil change direction and pupil change acceleration are determined; based on the pupil change speed, pupil change direction and pupil change acceleration, the eyeball movement is determined.

[0176] The pupil change speed can be obtained by calculating the pupil movement distance in consecutive frames and dividing it by the time interval corresponding to the change speed of each frame. Assuming that the pupil is The frame position is , in The frame position is , the time interval is , then the pupil change speed It can be calculated by referring to the following formula (1):

[0177] (1)

[0178] In addition, the direction of pupil change can be determined by the change trend of pupil position. This can include moving toward the center and spreading outward, quantifying the change trend of pupil position. Here, we assume a threshold When , is less than this threshold, it means that the pupil is moving toward the center. In other cases, it can be considered that the pupil is spreading outward. The specific calculation can be made by referring to the following formula (2):

[0179] (2)

[0180] The acceleration of pupil change can be calculated by the second-order derivative or differential method. For details, please refer to the following formula (3):

[0181] (3)

[0182] The solution provided in this embodiment calculates the relative position between the eyelid contour and the eyeball area, accurately determining the eyelid opening / closing ratio, and thus accurately judging the degree of eyelid opening / closing. This allows for real-time tracking of the pupil position within each frame of video, making it possible to calculate the pupil's speed, direction, and acceleration. By comprehensively considering the pupil's speed, direction, and acceleration, a comprehensive assessment of eye movement can be achieved, resulting in more accurate eye movement data and facilitating subsequent detection and diagnosis of eye diseases in patients.

[0183] In some embodiments, environmental changes are acquired in real time based on eye movements; a pupil inspection mode is determined based on environmental changes; the real-time position of the pupil is determined based on eye movements; the real-time pupil diameter is determined based on the real-time pupil position and eye features; and pupil changes are determined based on the pupil inspection mode and the real-time pupil diameter.

[0184] Based on the eye movement information obtained above, each time the eye changes, the current environmental changes, such as lighting conditions, are captured in real time. Based on the environmental changes and the multiple detection modes set in the above embodiments, the current pupil detection mode is determined. Then, based on the eye movement information, the real-time pupil position at each moment is determined, that is, the current position of the pupil in the eye.

[0185] The pupil's real-time position and the current eye characteristics are combined to determine the pupil's current diameter, i.e., the real-time pupil diameter. The pupil's changes are then determined based on the pupil inspection mode and the real-time pupil diameter.

[0186] In specific implementations, the patient's condition can be used to establish a correlation between eye zoom characteristics and environmental factors, and then a model can be built to determine environmental changes under different eye zoom conditions. In other implementations, the current image can be analyzed to determine the distribution of light within the image. This can then be combined with sensors within the eye monitor to determine the light intensity and distribution of the patient's environment, thereby inferring environmental changes.

[0187] The solution provided by this embodiment allows for real-time monitoring of eye movement, quickly capturing the ambient light in the eye's zoomed position. Based on the determined changes in the surrounding environment, the pupil examination mode is determined. This allows analysis of pupil changes to be closely linked to different examination modes, facilitating subsequent analysis of the patient's condition. Furthermore, it better meets the patient's eye examination needs. Changes in pupil diameter can directly reflect the pupil's response to different environmental stimuli, helping to assess the patient's visual accommodation ability and thus making it easier to analyze the patient's condition.

[0188] In some embodiments, an eye movement index is determined based on the pupil change speed, pupil change direction, and pupil change acceleration, and the eye movement condition is determined based on the eye movement index.

[0189] The eye movement is determined based on the pupil change speed, pupil change direction and pupil change acceleration, referring to the following formula (4):

[0190] (4)

[0191] in, represents the eye movement index; Indicates pupil change speed; The weight coefficient representing the pupil change speed; Indicates the average value of pupil change speed within the preset detection period; represents the standard deviation of pupil change speed; The weight coefficient representing the direction of pupil change; Indicates the direction of pupil change after quantification; The weight coefficient representing the acceleration of pupil change; represents the acceleration of pupil change; Indicates the average acceleration of pupil change during the preset detection period; represents the standard deviation of pupil acceleration;

[0192] The solution provided in this embodiment takes into account pupil change speed, pupil change direction, and pupil change acceleration, and designs a formula to calculate the eye zoom index, which is then used to reflect eye movement. This allows for a more comprehensive and accurate assessment of eye movement. Furthermore, the designed formula can digitize complex content, thereby more simply reflecting eye movement.

[0193] In some embodiments, the last inspection data is determined based on the current detection mode; based on the last inspection data, the last eyelid opening and closing degree, the last eyeball zoom degree and the last pupil change are determined; based on the eyelid opening and closing degree, eyeball movement, pupil changes, the last eyelid opening and closing degree, the last eyeball zoom degree and the last pupil change, the eye change trend is determined; based on the eye change trend, the current eye disease status is determined.

[0194] The last examination data can be understood as the examination data obtained from the last eye examination before the current examination, which may include the last eyelid opening and closing degree, eyeball movement, and pupil changes, that is, the last eyelid opening and closing degree, the last eyeball zoom degree, and the last pupil change.

[0195] Specifically, according to the current detection mode, the last inspection data matching the current detection mode is extracted from the database, the last inspection data is classified, and the last eyelid opening and closing degree, the last eyeball zoom degree and the last pupil change are determined. The eyelid opening and closing degree, eyeball movement and pupil change at the current moment are compared with the corresponding last eyelid opening and closing degree, the last eyeball zoom degree and the last pupil change respectively to determine the trend of eye changes compared with the last time under the current detection mode, that is, the eye change trend. For example, under the same detection mode, the eyelid opening and closing degree is larger than the last eyelid opening and closing degree. Based on the patient's condition, if the eye opening and closing degree gradually increases, it means that the condition has improved. At this time, it can be considered that the eye change trend is changing in a positive direction. Based on this eye change trend, it is determined whether the current eye disease has improved compared with the last time, and then combined with the initial diagnosis by the doctor, the current eye disease status is determined.

[0196] The solution provided in this embodiment integrates data from multiple dimensions, including eyelid opening and closing, eye movement, and pupil changes, providing a solid foundation for a comprehensive assessment of eye condition. By comparing current test data with the last test data, changing trends in eye condition can be accurately captured. By analyzing these trends, the current state of eye disease can be determined, providing a basis for subsequent assessment of whether the condition is improving.

[0197] Figure 3 This is a schematic diagram of a system for monitoring the progression of thyroid-related eye disease provided in one embodiment of the present application. Figure 3 As shown, the thyroid-related eye disease progression monitoring system 300 of this embodiment includes: a feature determination module 301 , a feature analysis module 302 , a pupil analysis module 303 , a state analysis module 304 , and a symptom analysis module 305 .

[0198] A feature determination module 301 is configured to obtain the eye monitoring video captured by the camera device, analyze the eye monitoring video, and determine eye features;

[0199] A feature analysis module 302 is used to analyze the eye features and determine the degree of eyelid opening and closing and eye movement;

[0200] The pupil analysis module 303 is used to determine pupil changes based on the eye movement;

[0201] The state analysis module 304 determines the current eye disease state according to the eyelid opening and closing degree, the eyeball movement, and the pupil change;

[0202] The symptom analysis module 305 is used to obtain and analyze historical eye disease diagnosis and treatment records to obtain historical eye disease status; compare the current eye disease status with the historical eye disease status to determine whether the thyroid-related eye disease has improved.

[0203] Optionally, the feature determination module 301 is specifically configured to:

[0204] Acquire and analyze a starting eye image, and determine whether eye deviation exists based on the image analysis result;

[0205] If it is determined that eye deviation exists, the eye deviation angle is determined based on the image analysis results;

[0206] The eye difference is determined according to the eye deviation angle and the historical eye disease diagnosis and treatment records, and the image capture method is adjusted according to the eye difference, and the eye monitoring video is obtained according to the adjusted image capture method.

[0207] Optionally, the eye detector includes a camera device; the feature determination module 301 is specifically configured to:

[0208] monitoring the displacement change of the eye detector in real time, and determining whether the spatial position of the eye detector has changed based on the displacement change;

[0209] If it is determined that there is a spatial position change, determining a horizontal position change amplitude based on the spatial position change;

[0210] determining whether to activate the camera device according to the horizontal position change amplitude;

[0211] If it is determined to start the camera device, acquiring and screening the image captured by the camera device to obtain the initial eye image;

[0212] Analyzing the initial eye image, and extracting eye features based on the image analysis result;

[0213] A structure boundary is determined based on the eye features, and the eye features within each structure are analyzed based on the structure boundaries to determine whether eye offset exists.

[0214] Optionally, the feature determination module 301 is specifically configured to:

[0215] determining an eyelid region based on the structure boundaries and eye features within each structure;

[0216] analyzing eye features of the eyelid region to determine an eyelid shadow area;

[0217] determining the eyelid shadow area according to the eyelid shadow region;

[0218] Obtaining the current lighting conditions and the spatial position of the camera device;

[0219] determining a desired eyelid shadow area according to the current lighting conditions and the spatial position;

[0220] Comparing the eyelid shadow area with the expected eyelid shadow area to determine whether the eyelid shadow area is larger than the expected eyelid shadow area;

[0221] If the eyelid shadow area is greater than the expected eyelid shadow area, it is determined that eye deviation exists.

[0222] Optionally, the feature determination module 301 is specifically configured to:

[0223] analyzing the eye monitoring video to determine changes in light and dark;

[0224] Determining a current detection mode according to the light and dark changes;

[0225] According to the current detection mode, the eye monitoring video is analyzed frame by frame to determine eye features.

[0226] Optionally, the feature analysis module is specifically used to:

[0227] Analyzing the eye features to determine the eyelid contour and eyeball area;

[0228] determining the relative position between the eyelid contour and the eyeball area according to the feature vector of the eye feature;

[0229] determining an eyelid opening / closing ratio according to the relative position, and determining an eyelid opening / closing degree according to the eyelid opening / closing ratio;

[0230] Determining the pupil position in each frame of video according to the eye features;

[0231] According to the pupil position in each frame of video, the pupil change speed, pupil change direction and pupil change acceleration are determined;

[0232] The eye movement condition is determined according to the pupil change speed, the pupil change direction and the pupil change acceleration.

[0233] Optionally, the pupil analysis module 303 is specifically configured to:

[0234] Based on the eye movement, real-time acquisition of environmental changes;

[0235] determining a pupil inspection mode according to the environmental changes;

[0236] determining the real-time position of the pupil according to the eye movement;

[0237] Determining a real-time pupil diameter based on the real-time pupil position and the eye features;

[0238] The pupil change is determined according to the pupil inspection mode and the real-time pupil diameter.

[0239] Optionally, the feature analysis module 302 is specifically configured to:

[0240] ;

[0241] in, represents the eye movement index; represents the pupil change speed; A weight coefficient representing the pupil change speed; represents the average value of the pupil change speed within a preset detection period; represents the standard deviation of the pupil change speed; A weight coefficient representing the pupil change direction; represents the quantified direction of pupil change; A weight coefficient representing the pupil change acceleration; represents the pupil change acceleration; represents the average acceleration of the pupil change acceleration within a preset detection period; represents the standard deviation of the pupil change acceleration;

[0242] The eye movement condition is determined according to the eye movement index.

[0243] Optionally, when determining the current eye disease state based on the eyelid opening and closing degree, the eyeball movement, and the pupil change, the state analysis module 304 is specifically configured to:

[0244] Determining the last inspection data according to the current inspection mode;

[0245] Determining the last eyelid opening and closing degree, the last eyeball zooming degree, and the last pupil change according to the last examination data;

[0246] Determining an eye change trend based on the eyelid opening and closing degree, the eyeball movement, the pupil change, the last eyelid opening and closing degree, the last eyeball zooming degree, and the last pupil change;

[0247] The current state of the eye disease is determined based on the eye change trend.

[0248] The system of this embodiment can be used to execute the method of any of the above embodiments. Its implementation principles and technical effects are similar and will not be described in detail here.

Claims

1. A method for monitoring the progression of thyroid-related eye disease, characterized in that: The progress monitoring method is applied to an eye detector, which includes a camera device and a data processing chip. The method is applied to the data processing chip; the method includes: Obtaining an eye monitoring video captured by the camera device, analyzing the eye monitoring video, and determining eye features; Analyzing the eye characteristics to determine the degree of eyelid opening and closing and eye movement; determining pupil changes according to the eye movement; Determining the current eye disease state according to the eyelid opening and closing degree, the eyeball movement, and the pupil change; Obtaining and analyzing historical eye disease diagnosis and treatment records to obtain historical eye disease status; comparing the current eye disease status with the historical eye disease status to determine whether the thyroid-related eye disease has improved; Analyzing the eye monitoring video to determine eye features includes: analyzing the eye monitoring video to determine changes in light and dark; Determining a current detection mode according to the light and dark changes; Analyze the eye monitoring video frame by frame according to the current detection mode to determine eye features; Analyzing the eye features to determine the degree of eyelid opening and closing and eye movement includes: Analyzing the eye features to determine the eyelid contour and eyeball area; determining the relative position between the eyelid contour and the eyeball area according to the feature vector of the eye feature; determining an eyelid opening / closing ratio according to the relative position, and determining an eyelid opening / closing degree according to the eyelid opening / closing ratio; Determining the pupil position in each frame of video according to the eye features; According to the pupil position in each frame of video, the pupil change speed, pupil change direction and pupil change acceleration are determined; determining the eye movement according to the pupil change speed, the pupil change direction, and the pupil change acceleration; Determining the current eye disease state based on the eyelid opening and closing degree, the eyeball movement, and the pupil change includes: Determining the last inspection data according to the current inspection mode; Determining the last eyelid opening and closing degree, the last eyeball zooming degree, and the last pupil change according to the last examination data; Determining an eye change trend based on the eyelid opening and closing degree, the eyeball movement, the pupil change, the last eyelid opening and closing degree, the last eyeball zooming degree, and the last pupil change; The current state of the eye disease is determined based on the eye change trend.

2. The method according to claim 1, characterized in that The obtaining of the eye monitoring video captured by the camera device includes: Acquire and analyze a starting eye image, and determine whether eye deviation exists based on the image analysis result; If it is determined that eye deviation exists, the eye deviation angle is determined based on the image analysis results; The eye difference is determined according to the eye deviation angle and the historical eye disease diagnosis and treatment records, and the image capture method is adjusted according to the eye difference, and the eye monitoring video is obtained according to the adjusted image capture method.

3. The method according to claim 2, characterized in that The acquiring and analyzing the initial eye image, and determining whether eye deviation exists according to the image analysis result, includes: monitoring the displacement change of the eye detector in real time, and determining whether the spatial position of the eye detector has changed based on the displacement change; If it is determined that there is a spatial position change, determining a horizontal position change amplitude based on the spatial position change; determining whether to activate the camera device according to the horizontal position change amplitude; If it is determined to start the camera device, acquiring and screening the image captured by the camera device to obtain the initial eye image; Analyzing the initial eye image, and extracting eye features based on the image analysis result; A structure boundary is determined based on the eye features, and the eye features within each structure are analyzed based on the structure boundaries to determine whether eye offset exists.

4. The method according to claim 3, characterized in that Analyzing the eye features within each structure according to the structure boundary to determine whether eye deviation exists includes: determining an eyelid region based on the structure boundaries and eye features within each structure; analyzing eye features of the eyelid region to determine an eyelid shadow area; determining the eyelid shadow area according to the eyelid shadow region; Obtaining the current lighting conditions and the spatial position of the camera device; determining a desired eyelid shadow area according to the current lighting conditions and the spatial position; Comparing the eyelid shadow area with the expected eyelid shadow area to determine whether the eyelid shadow area is larger than the expected eyelid shadow area; If the eyelid shadow area is greater than the expected eyelid shadow area, it is determined that eye deviation exists.

5. The method according to claim 1, characterized in that Determining pupil changes according to the eye movement includes: Based on the eye movement, real-time acquisition of environmental changes; determining a pupil inspection mode according to the environmental changes; determining the real-time position of the pupil according to the eye movement; Determining a real-time pupil diameter based on the real-time pupil position and the eye features; The pupil change is determined according to the pupil inspection mode and the real-time pupil diameter.

6. The method according to claim 1, characterized in that The eye movement condition is determined according to the pupil change speed, the pupil change direction and the pupil change acceleration, with reference to the following formula: ; Wherein, E represents the eye movement index; V represents the pupil change speed; a represents the weight coefficient of the pupil change speed; represents the average value of the pupil change speed within a preset detection period; represents the standard deviation of the pupil change speed; represents the weight coefficient of the pupil change direction; D represents the quantized pupil change direction; represents the weight coefficient of the pupil change acceleration; A represents the pupil change acceleration; represents the average acceleration of the pupil change acceleration within a preset detection period; represents the standard deviation of the pupil change acceleration; The eye movement condition is determined according to the eye movement index.

7. A system for monitoring the progression of thyroid-related eye disease, characterized in that: The method according to any one of claims 1 to 6 comprises: a feature determination module, configured to acquire an eye monitoring video captured by a camera device, analyze the eye monitoring video, and determine eye features; A feature analysis module, configured to analyze the eye features and determine the degree of eyelid opening and closing and eye movement; A pupil analysis module, configured to determine pupil changes based on the eye movement; A state analysis module determines the current state of eye disease based on the degree of eyelid opening and closing, the eyeball movement, and the pupil changes; The symptom analysis module is used to obtain and analyze historical eye disease diagnosis and treatment records to obtain historical eye disease status; compare the current eye disease status with the historical eye disease status to determine whether the thyroid-related eye disease has improved.

Images