Visual function detection method and system based on image analysis

Abstract

The present invention relates to the technical field of visual function detection, specifically a visual function detection method and system based on image analysis, including the following steps: collecting multi-wavelength reflection images of the fundus, adjusting the set wavelength parameters of the light source, activating the imaging device to receive images, denoising and contrast adjusting the collected images, and generating a multi-wavelength retinal image dataset. In the present invention, by collecting multi-wavelength images and performing meticulous denoising processing, the clarity and contrast of the images are significantly improved, bringing higher precision to damage recognition, reducing the chance of misdiagnosis. By calculating the light intensity gradient to map retinal damage, not only the damage range is accurately captured, but also the positioning of the damaged area is refined. The high-speed capture of the pupil dynamic response and its data analysis provide in-depth insights into eye movement patterns, making the evaluation of visual function more intuitive and comprehensive. By cross-verifying the visual field defect and pupil dynamic data, the comprehensiveness and accuracy of the evaluation are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of visual function detection, and particularly to a visual function detection method and system based on image analysis. Background Art

[0002] The technical field of visual function detection includes methods and systems for evaluating and analyzing the visual ability of the human eye, and is usually applied to the fields of ophthalmic medicine, visual science research, and vision-related human-machine interfaces. Visual function detection is a key means for evaluating eye health and visual performance, involving from basic visual acuity tests to complex visual function analyses, which can help doctors diagnose visual impairments, evaluate the effectiveness of visual correction measures, and perform early diagnoses of eye diseases.

[0003] Among them, the visual function detection method based on image analysis refers to using an image capture device and analysis software to evaluate visual function. It mainly captures image data of the eye, and then analyzes the response of the retina or eye movement patterns through image processing techniques, which can provide quantitative information about the visual state of the subject, and uses image analysis and processing algorithms to determine each parameter of visual function. The whole does not involve complex adjustment of computational models, but evaluates visual function by directly analyzing image data.

[0004] The prior art has obvious deficiencies in image detail analysis and comprehensive analysis, which limits its application effect in ophthalmic diagnosis and visual science research. Standardized visual tests lack adaptability to individual visual differences and cannot fully reveal complex retinal lesions or early functional losses. When dealing with dynamic visual information, existing methods usually fail to accurately reflect the minute changes of the pupil, resulting in insufficient evaluation of the dynamic characteristics of the pupil and making it difficult to effectively correlate retinal function and pupil response. The limitations may not only lead to incomplete diagnostic information, but also affect treatment decisions and the effectiveness evaluation of visual correction measures, especially in fields with high requirements for fine operations. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose a visual function detection method based on image analysis.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: A visual function detection method based on image analysis, including the following steps:

[0007] S1: Collect multi-wavelength reflection images of the fundus, adjust the set wavelength parameters of the light source, activate the imaging device to receive images, and perform denoising and contrast adjustment on the collected images to generate a multi-wavelength retinal image dataset;

[0008] S2: Based on the multi-wavelength retinal image dataset, calculate the difference between the light intensity of each pixel and the light intensity of surrounding pixels, collect the light intensity gradients, reveal the areas of retinal damage and functional defects according to the difference calculation results, map the scope of retinal damage, and obtain the visual field defect area image;

[0009] S3: Capture the dynamic process of the pupil's response to light changes through high-speed photography, adjust the shooting frequency to match the speed of pupil constriction and dilation, measure the pupil diameter change for each frame of image, analyze the response speed of the pupil to instantaneous light intensity changes according to the measurement results, judge the sensitivity of pupil regulation, and generate a pupil detection report;

[0010] S4: Integrate the visual field defect area image and the pupil detection report, perform cross-verification on the two types of data, analyze the status of visual function, and generate a comprehensive visual function evaluation result.

[0011] As a further solution of the present invention, the steps for obtaining the multi-wavelength retinal image dataset are as follows:

[0012] S111: Set the light source wavelength to match the retinal absorption characteristics, adjust the light source to cover all spectra from ultraviolet to infrared, and obtain the adjusted light source wavelength parameters;

[0013] S112: Utilize the adjusted light source wavelength parameters to activate the imaging device and calibrate the light-sensitive settings, initialize the capture efficiency and quality of multi-wavelength images, and generate a multi-wavelength original image set;

[0014] S113: Perform signal processing on the multi-wavelength original image set, execute denoising and contrast enhancement, and use the formula:

[0015] ;

[0016] Calculate the pixel values of the enhanced image , and obtain the multi-wavelength retinal image dataset, where represents the single image pixel value in the multi-wavelength original image set, represents the pixel average value of represents the pixel standard deviation of

[0017] As a further solution of the present invention, the steps for obtaining the light intensity gradient data are as follows:

[0018] S211: Based on the multi-wavelength retinal image dataset, grab the light intensity of each pixel in the image data to obtain the initial light intensity dataset;

[0019] S212: Based on the initial light intensity dataset, use the formula:

[0020] ;

[0021] Calculate the light intensity difference between each pixel and its neighboring pixels , and obtain a light intensity difference data set, where represents the light intensity of pixel , represents the set of pixels around point , and is the number of pixels in the set;

[0022] S213: Analyze the light intensity difference data set, set a threshold , and identify the regions where the light intensity change exceeds the threshold . Mark the corresponding regions as regions with significant light intensity gradient changes, and generate light intensity gradient data.

[0023] As a further solution of the present invention, the steps for obtaining the image of the visual field defect region are as follows:

[0024] S221: Based on the light intensity gradient data, determine the regions with significant light intensity changes, compare them with a critical threshold, and mark the parts that exceed the critical threshold as potential retinal damage regions, generating damage identification data;

[0025] S222: Based on the damage identification data, perform spatial mapping on the potential retinal damage regions, depict the boundaries of the damage regions and superimpose them on the standard model of the retina, generating a retinal damage map;

[0026] S223: Using the retinal damage map, convert the mapping of the damage region into a visual field defect map, emphasize the damage region through differential color marking, and visually display the location and scope of the retinal damage to obtain the image of the visual field defect region.

[0027] As a further solution of the present invention, the steps for measuring the change in pupil diameter are as follows:

[0028] S311: Record the dynamic process of the pupil under continuous light changes through a high-speed camera, adjust the shooting frequency of the camera to match the contraction and dilation of the pupil each time, and generate a pupil dynamic video;

[0029] S312: Extract the pupil image of each frame from the pupil dynamic video, analyze the geometric features of the pupil, and accurately measure the diameter of the pupil in each frame to obtain pupil diameter sequence data;

[0030] S313: Perform frame-by-frame difference processing on the pupil diameter sequence data, using the formula:

[0031] ;

[0032] Calculate the change in pupil diameter between the i-th frame and the previous frame to generate pupil diameter change data, where and represent the pupil diameters in two consecutive frames respectively.

[0033] As a further solution of the present invention, the steps for obtaining the pupil detection report are as follows:

[0034] S321: Based on the pupil diameter change data, use the formula:

[0035] ;

[0036] Calculate the response speed of the pupil to each change in light intensity to generate pupil response speed data, where represents the change in pupil diameter, represents the time interval;

[0037] S322: Analyze the pupil response speed data, perform statistical processing on the data, evaluate the sensitivity of pupil regulation, and judge the adaptability and regulation speed of the pupil to changes in light intensity to obtain the pupil regulation sensitivity evaluation result;

[0038] S323: Integrate the pupil response speed data and the pupil regulation sensitivity evaluation result, compare the data with the health standard, evaluate the pupil function, and generate a pupil detection report.

[0039] As a further solution of the present invention, the steps for obtaining the comprehensive visual function evaluation result are as follows:

[0040] S411: Integrate the visual field defect area image and the pupil detection report, count the coordinates of the visual field defect and the time series of pupil dynamic changes to obtain the retina and pupil data set;

[0041] S412: Based on the retina and pupil data set, perform data cross-validation, confirm the possibility and scope of visual function abnormality, and generate a visual function abnormality correlation analysis result;

[0042] S413: Based on the visual function abnormality correlation analysis result, use the formula:

[0043] ;

[0044] Calculate the comprehensive visual function evaluation score to generate the comprehensive visual function evaluation result, where represents the retina damage score obtained from the visual function abnormality correlation analysis, is the mean of all response durations in the pupil response dataset, is the total number of data items.

[0045] A visual function detection system based on image analysis, comprising:

[0046] The light source setting module sets the light source wavelength to match the retinal absorption characteristics, adjusts the light source to cover all spectra, activates the imaging device and calibrates the photosensitive settings, performs denoising and contrast enhancement, calculates the pixel values of the enhanced image, and obtains a multi-wavelength retinal image dataset;

[0047] The retinal analysis module, based on the multi-wavelength retinal image dataset, grabs the light intensity data of each pixel point in the image data, calculates the difference in light intensity between each pixel point and its neighboring pixel points, identifies the regions where the light intensity change exceeds the threshold, compares them with the critical threshold, marks the parts exceeding the critical threshold as potential retinal damage regions, performs spatial mapping on the potential retinal damage regions, and emphasizes the damaged regions through differential color marking to obtain an image of the visual field defect region;

[0048] The pupil dynamic monitoring module records the dynamic process of the pupil in continuous light changes through a high-speed camera, extracts the pupil image of each frame, analyzes the geometric features of the pupil, accurately measures the diameter of the pupil in each frame, calculates the change in pupil diameter between each frame and the previous frame and the response speed of the pupil to each light intensity change, determines the adaptability and adjustment speed of the pupil to light intensity changes, compares with the healthy standard, evaluates the pupil function, and generates a pupil detection report;

[0049] The visual function comprehensive evaluation module integrates the visual field defect region image and the pupil detection report, statistically analyzes the coordinates of the visual field defect and the time series of pupil dynamic changes, performs data cross-validation, calculates the comprehensive visual function evaluation score, and generates a comprehensive visual function evaluation result.

[0050] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0051] In the present invention, by collecting multi-wavelength images and performing detailed denoising processing, the clarity and contrast of the images are greatly improved, bringing higher precision for damage identification, reducing the chance of misdiagnosis. By calculating the light intensity gradient to map retinal damage, not only the damage range is accurately captured, but also the positioning of the damaged region is refined. The high-speed capture of the pupil's dynamic response and its data analysis provide in-depth insights into eye movement patterns, making the evaluation of visual function more intuitive and comprehensive. By cross-validating the visual field defect and pupil dynamic data, the comprehensiveness and accuracy of the evaluation are enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is the main flowchart of the present invention;

[0053] Figure 2 This is the flowchart for obtaining the multi-wavelength retinal image dataset of the present invention;

[0054] Figure 3 This is the flowchart for obtaining the light intensity gradient data of the present invention;

[0055] Figure 4 This is the flowchart for obtaining the image of the visual field defect area of the present invention;

[0056] Figure 5 This is the flowchart for measuring the change in pupil diameter of the present invention;

[0057] Figure 6 This is the flowchart for obtaining the pupil detection report of the present invention;

[0058] Figure 7 This is the flowchart for obtaining the comprehensive visual function evaluation result of the present invention. Detailed implementation manners

[0059] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0060] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0061] Please refer to Figure 1 , the visual function detection method based on image analysis, includes the following steps:

[0062] S1: Collect multi-wavelength reflection images of the fundus, adjust the set wavelength parameters of the light source, activate the imaging device to receive images, and perform denoising and contrast adjustment on the collected images to generate a multi-wavelength retinal image dataset;

[0063] S2: Based on the multi-wavelength retinal image dataset, calculate the difference between the light intensity of each pixel point and the light intensity of the surrounding pixels, collect the light intensity gradient, reveal the retinal damage and functional defect areas according to the difference calculation result, map the damage range of the retina, and obtain the image of the visual field defect area;

[0064] S3: Capture the dynamic process of the pupil's response to light changes through high-speed photography, adjust the shooting frequency to match the speed of pupil contraction and dilation, measure the change in pupil diameter for each frame of the image, analyze the response speed of the pupil to instantaneous light intensity changes based on the measurement results, determine the sensitivity of pupil regulation, and generate a pupil detection report;

[0065] S4: Integrate the image of the visual field defect area and the pupil detection report, cross-validate the two types of data, analyze the status of visual function, and generate a comprehensive visual function evaluation result.

[0066] The multi-wavelength retinal image dataset includes wavelength distribution records, contrast adjustment results, and noise indices; the image of the visual field defect area includes the damage boundary, the size of the affected area, and the abnormal light intensity area; the pupil detection report includes the maximum pupil diameter, the minimum pupil diameter, and the change rate; the comprehensive visual function evaluation result includes the analysis result of visual function integrity, the pupil response health index, and the retinal damage correlation.

[0067] Please refer to Figure 2 , and the steps for obtaining the multi-wavelength retinal image dataset are as follows:

[0068] S111: Set the light source wavelength to match the retinal absorption characteristics, adjust the light source to cover all spectra from ultraviolet to infrared, and obtain the adjusted light source wavelength parameters;

[0069] When setting the light source wavelength to adapt to the retinal absorption characteristics, conduct a detailed analysis of the spectral range of the light source, including measuring the output energy of different types of light sources such as LEDs and lasers at different wavelengths, using a spectral analyzer to record the intensity of light at each wavelength to identify which bands can be most effectively absorbed by retinal tissue. Next, based on the obtained spectral data, manually adjust the settings on the light source controller to ensure that the wavelength output of the light source can be adjusted as needed. For example, if the infrared and near-infrared bands show higher absorption efficiency, the operator will adjust the ability of the light source to emit specific wavelengths, and the specific operations include adjusting the current input of the light source and adjusting the position of the wavelength filter to ensure a wide spectral coverage from ultraviolet to infrared.

[0070] S112: Use the adjusted light source wavelength parameters to activate the imaging device and calibrate the photosensitive settings, initialize the capture efficiency and quality of multi-wavelength images, and generate a multi-wavelength raw image set;

[0071] In the process of activating and calibrating a camera device to capture multi-wavelength images using the adjusted light source wavelength parameters, first, the hardware settings of the camera device are checked and configured, including adjusting the lens focus and aperture of the camera to adapt to the light intensity at different wavelengths. The operator needs to manually set the exposure time and sensitivity according to the wavelength adjustment parameters, which is usually done through the control panel to ensure that the camera device can receive uniform and clear images at each wavelength. Subsequently, a series of test shots are taken, and the image quality obtained under different settings is observed. For example, the clarity and color accuracy of the image are tested under ultraviolet light with a lower wavelength, and the exposure and ISO settings are adjusted to reduce image noise and improve resolution. The process not only depends on the technical operation of the operator but also requires continuous adjustment of the settings by observing the obtained images to ensure that the final image can be effectively used for subsequent medical analysis and diagnosis, thus generating a multi-wavelength raw image set.

[0072] S113: Perform signal processing on the multi-wavelength raw image set, including denoising and contrast enhancement, using the formula:

[0073] ;

[0074] Calculate the pixel values of the enhanced image , to obtain a multi-wavelength retinal image data set, where represents the pixel value of a single image in the multi-wavelength raw image set, represents the average pixel value, represents the pixel standard deviation;

[0075] In a set of image data, the pixel value of a certain pixel in the original image is 120, the average pixel value of the entire image is 100, and the standard deviation is 15. First, calculate the absolute value of the difference between and

[0076] ;

[0077] Put the difference value into the formula for square root and standard deviation processing:

[0078] ;

[0079] Then use to standardize this result:

[0080] ;

[0081] The calculation result represents the pixel value after enhancement processing, compared with the original , while maintaining the original brightness, it improves the contrast of the image, making the details in the image more obvious, which helps in the recognition of details during the diagnosis process. Especially when identifying and analyzing fundus images, fine blood vessels and tissue structures are more easily observable and analyzable, providing a clearer and more accurate retinal image, thus better supporting clinical decision-making.

[0082] Please refer to Figure 3 , the steps for obtaining the light intensity gradient data are as follows:

[0083] S211: Based on the multi-wavelength retinal image dataset, data capture of the light intensity of each pixel point in the image data is performed to obtain the initial light intensity dataset;

[0084] First, select an image from the multi-wavelength retinal image dataset. The selection process involves evaluating the clarity, contrast, and color depth of the image to ensure that the selected image has sufficient quality for in-depth analysis. Specifically, first check the pixel resolution of each image to ensure that it reaches or exceeds the specified resolution standard, because high resolution can provide more details and help with subsequent light intensity calculations. Then, perform color correction on the image. During the correction process, adjust the image color according to the light color distribution of different wavelengths in the image to make it reflect the more real retinal state. In addition, noise is an important factor affecting image quality. By comparing the background noise levels of different images, select the image with the lowest noise for analysis.

[0085] S212: Based on the initial light intensity dataset, use the formula:

[0086] ;

[0087] Calculate the light intensity difference between each pixel point and its neighboring pixel points , to obtain the light intensity difference dataset, where, represents the light intensity of pixel point , represents the set of pixels around point , is the number of pixels in the set;

[0088] Set the light intensity of the central pixel point to 150. Assume that there are 8 pixel points around it, and their light intensity values are 152, 148, 147, 149, 153, 151, 150, 148 respectively. First, calculate the average light intensity of these 8 neighboring pixels:

[0089] ;

[0090] Subtract the light intensity of the central pixel from the average value to obtain the light intensity difference:

[0091] ;

[0092] Calculation result indicates that the light intensity difference of the central pixel is very small compared to its surrounding pixels. This means that within the target area, the change in light intensity of the retinal image is not sufficient to be identified as a damaged or diseased area, providing a basis for identifying the retinal areas that require further diagnosis and helping to detect and treat retinal diseases at an early stage.

[0093] S213: Analyze the light intensity difference data set, set a threshold , identify the areas where the light intensity change exceeds the threshold , mark the corresponding areas as areas with significant changes in light intensity gradient, and generate light intensity gradient data;

[0094] During the analysis of the light intensity difference data set, it is necessary to determine which areas have light intensity changes that exceed the normal range. First, obtain data from the light intensity difference data set, which represents the relative difference in light intensity between each pixel and its surrounding pixels. Next, calculate the average value and standard deviation of the light intensity change based on the light intensity distribution of the entire data set, and set a threshold , which is usually set as the average light intensity change plus twice the standard deviation to ensure that only significant changes are marked. Through this threshold, all pixel points with light intensity changes exceeding are selected. Then, these pixel points are marked as areas with significant changes in light intensity gradient. The marking of these areas not only helps to identify potential retinal damage but also provides a basis for further medical diagnosis.

[0095] Please refer to Figure 4 , and the steps for obtaining the image of the visual field defect area are as follows:

[0096] S221: Based on the light intensity gradient data, determine the areas with significant light intensity changes, compare them with the critical threshold, and the parts exceeding the critical threshold are marked as potential retinal damage areas, generating damage identification data;

[0097] According to the foregoing, determine the areas on the retina with significant light intensity changes, and then compare the light intensity differences in the areas with significant light intensity changes with the critical threshold. This critical threshold is used to distinguish between normal light intensity changes and changes indicating potential damage. Compare the light intensity difference of each pixel point in the area with significant light intensity changes with the critical threshold. If it exceeds this threshold, the pixel is marked as a potential damage area.

[0098] ​S222: Based on the damage identification data, spatially map the potential retinal damage area, depict the boundary of the damage area and superimpose it on the standard model of the retina to generate a retinal damage map;

[0099] The marked potential lesion areas are mapped in detail, first using basic image processing operations such as dilation and erosion to enhance the visual recognition of the marked areas. Then, contour tracing is applied to each marked area to determine the precise boundaries. The contours are then superimposed on a standard retinal model, and the exact position and shape of each contour is adjusted according to the retinal anatomy to ensure a match with the actual retina.

[0100] S223: using the retinal damage map, converting the mapping of the damaged area into a visual field defect map, emphasizing the damaged area through differential color marking, visually displaying the location and range of the retinal damage, and obtaining an image of the visual field defect area;

[0101] The aforementioned retinal damage map is converted into a visual field loss map that can be displayed intuitively. First, a series of color codes are defined to represent different degrees of damage: mild, moderate, and severe damage are represented by green, yellow, and red, respectively. Next, the area of ​​each damage level is colored accordingly according to the degree of damage to ensure immediate visual identification. Finally, these color-marked areas are synthesized into the final visual field loss image, which is completed through simple image overlay technology and color processing without relying on any external software, and can intuitively evaluate and analyze the damage status of the retina.

[0102] See also Figure 5 , the measurement steps of pupil diameter change are:

[0103] S311: Record the dynamic process of the pupil in the continuous light change by a high-speed camera, adjust the shooting frequency of the camera, match the contraction and expansion of the pupil each time, and generate a pupil dynamic video;

[0104] The dynamic process of the pupil in continuous light changes is recorded by a high-speed camera. In the specific process, the high-speed camera is first set to aim at the subject's eyes, and the focal length and exposure parameters of the camera are adjusted to adapt to the indoor light conditions to ensure image clarity. Subsequently, by comparing the pupil images before and after the light changes, each change of the pupil is captured frame by frame. At this time, each frame of the image needs to be sent to the computer through real-time image transmission. On the computer side, these image data will be received and stored, and each frame of the image will be marked with a timestamp to facilitate subsequent analysis of the relationship between pupil changes and time. Next, the pupil area is located from each frame of the image, the diameter of the pupil is measured, the pupil boundary in the image is identified, and its size is calculated.

[0105] S312: Extract the pupil image of each frame from the pupil dynamic video, analyze the geometric features of the pupil, and accurately measure the diameter of the pupil in each frame to obtain the pupil diameter sequence data;

[0106] Extract the pupil image of each frame from the generated pupil dynamic video. During the process, each frame of the image first goes through a preprocessing stage to adjust the contrast and brightness of the image to highlight the pupil area. Then, edge detection is used to identify the pupil boundary, mainly relying on detecting the color and brightness changes in the image. When an obvious color jump is detected, it is marked as the edge of the pupil. Each measurement of the pupil diameter is achieved by calculating the maximum and minimum boundary distances of the pupil in the edge detection result, which can effectively reduce the influence of ambient light and the error caused by the subject's blinking. After the measurement is completed, all the pupil diameter data are collected and sorted to form a continuous data sequence for analyzing the changing trend of the pupil diameter over time, thereby providing a detailed insight into the dynamic changes of the pupil.

[0107] S313: Perform frame-by-frame differential processing on the pupil diameter sequence data using the formula:

[0108] ;

[0109] Calculate the change in pupil diameter between the i-th frame and the previous frame , generating pupil diameter change data, where, and represent the pupil diameters in two consecutive frames respectively;

[0110] Assume that the pupil diameters in two consecutive frames are 2.4 mm and 2.5 mm respectively, and the calculation process is , indicating that the pupil diameter has increased by 0.1 mm from the previous frame to the current frame. This result shows the response speed and adjustment ability of the pupil to light, and further research on the changes can help understand the health status of the visual system; and represent the pupil diameters in two consecutive frames respectively. The formula calculates the change amount by directly comparing the pupil diameter differences between adjacent frames, providing the instant response data of the pupil to light changes simply and effectively.

[0111] Please refer to Figure 6 , and the steps to obtain the pupil detection report are:

[0112] S321: Based on the pupil diameter change data, use the formula:

[0113] ;

[0114] Calculate the response speed of the pupil to each light intensity change , generating pupil response speed data, where, Represents the change in pupil diameter, represents the time interval;

[0115] Consider a typical situation where the pupil diameter changes from 4.0 mm to 4.5 mm within 0.1 seconds. Calculate the response speed according to the formula: . This result indicates that the response speed of the pupil is 5.0 millimeters per second. This relatively fast change speed shows that the pupil has high sensitivity to changes in light intensity. This result indicates that the pupil regulation function is good and can quickly respond to changes in external light. The speed index helps to diagnose whether there is an abnormality in the pupil response function.

[0116] S322: Analyze the pupil response speed data, perform statistical processing on the data, evaluate the sensitivity of pupil regulation, judge the adaptability and regulation speed of the pupil to changes in light intensity, and obtain the evaluation result of pupil regulation sensitivity;

[0117] Based on the pupil response speed data, conduct a detailed statistical analysis to evaluate the sensitivity of pupil regulation. First, sort and classify the collected response speed data. To ensure the accuracy of data processing, manually check each data point and exclude any outliers or incorrect inputs. Then, calculate the mean and standard deviation of the data. Calculating the mean provides the central tendency of the pupil response speed, while the standard deviation reflects the variability of the pupil response speed. These two statistical indicators are obtained by calculating the distance of each data point from the mean, which can quantitatively describe the sensitivity of pupil regulation and provide a scientific basis for further evaluation of the pupil health status.

[0118] S323: Integrate the pupil response speed data and the evaluation result of pupil regulation sensitivity, compare the data with the health standard, evaluate the pupil function, and generate a pupil detection report;

[0119] After completing the evaluation of the pupil response speed and regulation sensitivity, comprehensively use these data for a comprehensive evaluation of the pupil health status. First, compare the previously calculated statistical data with the health standard, which is established based on a large amount of research and clinical data to ensure the reliability of the evaluation results. In the comparative analysis, pay special attention to the data points that deviate from the normal range. Each such data point will be detailedly recorded and analyzed, including its possible health risks and the reasons for further diagnosis. In addition, considering the stability and adaptability of pupil regulation, combine these characteristics with the data of pupil response speed and sensitivity. By analyzing how each parameter affects the overall performance of the pupil one by one, provide data support for the final health evaluation report.

[0120] Please refer to Figure 7 , the steps to obtain the comprehensive visual function evaluation result are as follows:

[0121] S411: Integrate the images of the visual field defect areas and the pupil detection reports, count the coordinates of the visual field defects and the time series of the dynamic changes of the pupils, and obtain the retinal and pupil data sets;

[0122] When integrating the images of the visual field defect areas and the pupil detection reports, first obtain the retinal images through high-resolution scanning, manually mark the edges and centers of the retinal damage areas, and use image processing techniques, such as edge detection and region growing algorithms, for each marked area to determine the exact coordinates and areas of the damage areas. Subsequently, through a non-invasive eye movement tracking device, record the dynamic response of the pupils to light stimuli. This device captures the time series data of the changes in pupil size and position movement, and evaluates the response speed and amplitude of the pupils by quantitatively analyzing the changes. Synchronize the captured images and time series data, and associate the retinal damage data with the pupil response data through data matching techniques to form a comprehensive data set that contains both the spatial information of the damage and the temporal response characteristics of the pupils.

[0123] S412: Based on the retinal and pupil data sets, conduct data cross-validation, confirm the possibility and scope of visual function abnormalities, and generate the analysis results of the correlation of visual function abnormalities;

[0124] When conducting the analysis of the correlation of visual function abnormalities, first extract the retinal damage data and the pupil response data from the comprehensive data set respectively, and conduct preliminary statistical analysis on the data, including the calculation of the mean value, variance, and distribution characteristics. The statistical values help to understand the basic behavior of the data and the possible abnormal patterns. Then, use the method of data cross-validation to determine the correlation between the retinal damage and the pupil response, including calculating the correlation coefficient between the two sets of data to evaluate the direct connection between them. After that, by establishing a logistic regression model, use the retinal damage data as the independent variable and the pupil response characteristics as the dependent variable to minimize the prediction error, and finally determine the probability and the scope of the visual function abnormalities. The analysis process not only considers individual data points but also analyzes the overall trend in the data set, ensuring the accuracy and reliability of the results.

[0125] S413: Based on the analysis results of the correlation of visual function abnormalities, use the formula:

[0126] ;

[0127] Calculate the comprehensive visual function assessment score , and generate the comprehensive visual function assessment result, where represents the retinal damage score obtained from the analysis of the correlation of visual function abnormalities, is the mean value of all response durations in the pupil response data set, is the total number of data items;

[0128] Set S = 85 to represent the retinal damage score obtained from the visual function abnormality correlation analysis, M = 75 to represent the mean of all response durations in the pupil response dataset, and H = 10 to be the total number of data items. Inserting the values, the formula becomes:

[0129] ;

[0130] Calculated as:

[0131] ;

[0132] The result shows that the comprehensive visual function evaluation score is 0.316, indicating a low correlation between retinal damage and pupil dynamic response in the current dataset, thus evaluating a relatively low possibility of visual function abnormality, which helps clinicians more accurately judge the retinal and pupil function status in diagnosis and treatment.

[0133] A visual function detection system based on image analysis, including:

[0134] The light source setting module sets the light source wavelength to match the retinal absorption characteristics, adjusts the light source to cover all spectra, activates the imaging device and calibrates the light-sensitive settings, performs denoising and contrast enhancement, calculates the pixel values of the enhanced image, and obtains a multi-wavelength retinal image dataset;

[0135] The retinal analysis module, based on the multi-wavelength retinal image dataset, grabs the light intensity data of each pixel point in the image data, calculates the difference in light intensity between each pixel point and its neighboring pixel points, identifies the regions where the light intensity change exceeds the threshold, compares with the critical threshold, marks the part exceeding the critical threshold as potential retinal damage regions, performs spatial mapping on the potential retinal damage regions, and emphasizes the damaged regions by differential color marking to obtain an image of the visual field defect region;

[0136] The pupil dynamic monitoring module records the dynamic process of the pupil in continuous light changes through a high-speed camera, extracts the pupil image of each frame, analyzes the geometric features of the pupil, accurately measures the diameter of the pupil in each frame, calculates the change in pupil diameter between the current frame and the previous frame and the response speed of the pupil to each light intensity change, judges the adaptability and adjustment speed of the pupil to light intensity changes, compares with the healthy standard, evaluates the pupil function, and generates a pupil detection report;

[0137] The visual function comprehensive evaluation module integrates the image of the visual field defect region and the pupil detection report, counts the coordinates of the visual field defect and the time series of pupil dynamic changes, performs data cross-validation, calculates the comprehensive visual function evaluation score, and generates a comprehensive visual function evaluation result.

[0138] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A visual function detection method based on image analysis, characterized in that: The following steps are involved: S1: Collect multi-wavelength reflectance images of the fundus, adjust the wavelength parameters of the light source, activate the camera to receive images, denoise and adjust the contrast of the collected images, and generate a multi-wavelength retinal image dataset; S2: Based on the multi-wavelength retinal image data set, the difference between the light intensity of each pixel and the light intensity of surrounding pixels is calculated, the light intensity gradient is collected, and the retinal damage and functional defect areas are revealed according to the difference calculation results, the retinal damage range is mapped, and the visual field defect area image is obtained; S3: Capture the dynamic process of pupil changes in response to light through high-speed video, adjust the shooting frequency to match the speed of pupil contraction and expansion, measure the change of pupil diameter for each frame of image, analyze the reaction speed of pupil to instantaneous light intensity change based on the measurement results, determine the sensitivity of pupil adjustment, and generate a pupil detection report; S4: combining the visual field defect area image and the pupil detection report, cross-validating the two data, analyzing the state of visual function, and generating a comprehensive visual function evaluation result; The steps for obtaining the comprehensive visual function evaluation result are as follows: S411: Integrate the visual field defect area image and the pupil detection report, mark the edge and center of the retinal damage area, record the dynamic response of the pupil to light stimulation, count the coordinates of the visual field defect and the time series of the pupil dynamic change, and obtain a retinal and pupil data set; S412: Based on the retinal and pupil data set, data cross-validation is performed, and a logistic regression model is established, using the retinal damage data as an independent variable and the pupil reaction characteristics as a dependent variable to confirm the possibility and scope of visual function abnormality and generate a visual function abnormality correlation analysis result; S413: Based on the visual function abnormality correlation analysis results, the formula is used: ; Calculate the comprehensive visual function assessment score , generate comprehensive visual function assessment results, where represents the retinal damage score obtained from the correlation analysis of visual function abnormalities, is the mean of all reaction times in the pupil reaction dataset, is the total number of data items.

2. The method for detecting visual function based on image analysis according to claim 1, characterized in that: The steps of acquiring the multi-wavelength retinal image dataset are as follows: S111: Setting the wavelength of the light source to match the absorption characteristics of the retina, adjusting the light source to cover the entire spectrum from ultraviolet to infrared, and obtaining the adjusted wavelength parameters of the light source; S112: activating the camera device and calibrating the photosensitivity settings using the adjusted light source wavelength parameters, initializing the capture efficiency and quality of the multi-wavelength image, and generating a multi-wavelength original image set; S113: Perform signal processing on the multi-wavelength original image set, perform denoising and contrast enhancement, using the formula: ; Calculate the pixel value of the enhanced image , we get a multi-wavelength retinal image dataset, where represents a single image pixel value in the multi-wavelength raw image set, represent The average pixel value, represent The pixel standard deviation.

3. The visual function detection method based on image analysis according to claim 2, characterized in that: The steps for obtaining the light intensity gradient data are: S211: Based on the multi-wavelength retinal image dataset, data capture of the light intensity of each pixel in the image data is performed to obtain an initial light intensity dataset; S212: Based on the initial light intensity data set, using the formula: ; Calculate the light intensity difference between each pixel and its neighboring pixels , and obtain the light intensity difference data set, where Represents pixel The light intensity, Representative Points The surrounding pixels are is the number of pixels in the set; S213: Analyze the light intensity difference data set and set a threshold , identifying light intensity changes exceeding a threshold The corresponding area is marked as the area with significant changes in light intensity gradient, and light intensity gradient data is generated.

4. The method for detecting visual function based on image analysis according to claim 3, characterized in that: The steps of acquiring the image of the visual field defect area are: S221: Based on the light intensity gradient data, determine the area where the light intensity changes significantly, compare it with the critical threshold, and mark the part exceeding the critical threshold as a potential retinal damage area to generate damage identification data; S222: Based on the damage identification data, spatially map the potential retinal damage area, depict the boundary of the damage area and superimpose it on the standard model of the retina to generate a retinal damage map; S223: Using the retinal damage map, converting the mapping of the damaged area into a visual field defect map, emphasizing the damaged area through differential color marking, intuitively displaying the location and range of the retinal damage, and obtaining a visual field defect area image.

5. The method for detecting visual function based on image analysis according to claim 4, characterized in that: The measuring steps of the pupil diameter change are: S311: Record the dynamic process of the pupil in the continuous light change by a high-speed camera, adjust the shooting frequency of the camera, match the contraction and expansion of the pupil each time, and generate a pupil dynamic video; S312: extracting a pupil image of each frame from the pupil dynamic video, analyzing the geometric features of the pupil, and accurately measuring the diameter of the pupil of each frame to obtain pupil diameter sequence data; S313: Perform frame-by-frame differential processing on the pupil diameter sequence data, using the formula: ; Calculate the change in pupil diameter between the i-th frame and the previous frame , generate pupil diameter change data, where, and Represent the pupil diameters in two consecutive frames respectively.

6. The method for detecting visual function based on image analysis according to claim 5, characterized in that: The steps for obtaining the pupil detection report are: S321: Based on the pupil diameter change data, the formula is used: ; Calculate the pupil's reaction speed to each change in light intensity , generate pupil response speed data, where represents the change in pupil diameter, Indicates a time interval; S322: Analyze the pupil response speed data, perform statistical processing on the data, evaluate the sensitivity of pupil adjustment, determine the pupil's adaptability to light intensity changes and the adjustment speed, and obtain a pupil adjustment sensitivity evaluation result; S323: Integrate the pupil response speed data and the pupil accommodation sensitivity evaluation result, compare the data with the health standard, evaluate the pupil function, and generate a pupil detection report.

7. A visual function detection system based on image analysis, characterized in that: The visual function detection system based on image analysis is used to execute the visual function detection method based on image analysis according to any one of claims 1 to 6, comprising: The light source setting module sets the wavelength of the light source to match the absorption characteristics of the retina, adjusts the light source to cover all spectra, activates the camera device and calibrates the photosensitivity settings, performs denoising and contrast enhancement, calculates the pixel values ​​of the enhanced image, and obtains a multi-wavelength retinal image dataset; The retinal analysis module captures the light intensity of each pixel in the image data based on the multi-wavelength retinal image data set, calculates the light intensity difference between each pixel and the adjacent pixel, identifies the area where the light intensity change exceeds the threshold, compares it with the critical threshold, and marks the part exceeding the critical threshold as a potential retinal damage area. The potential retinal damage area is spatially mapped, and the damaged area is emphasized by differential color marking to obtain an image of the visual field defect area; The pupil dynamic monitoring module records the dynamic process of the pupil in continuous light changes through a high-speed camera, extracts the pupil image of each frame, analyzes the geometric characteristics of the pupil, and accurately measures the pupil diameter of each frame, calculates the change in pupil diameter between the previous frame and the pupil's reaction speed to each light intensity change, determines the pupil's adaptability and adjustment speed to light intensity changes, compares it with the health standard, evaluates pupil function, and generates a pupil detection report; The comprehensive visual function evaluation module integrates the visual field defect area image and pupil detection report, counts the coordinates of the visual field defect and the time series of pupil dynamic changes, performs data cross-validation, calculates the comprehensive visual function evaluation score, and generates a comprehensive visual function evaluation result.

Images