Imaging method of a table fundus camera and table fundus camera

Abstract

The application discloses an imaging method of a desktop fundus camera and the desktop fundus camera, and relates to the field of ophthalmic detection. The method comprises the following steps: acquiring an eye image of a target object, and determining identity information of the target object according to the eye image; determining an eye parameter of the target object according to the identity information; determining a light irradiation parameter and a detection position during eye detection based on the eye parameter; detecting an eye position of the target object in real time; and when it is determined that the eye position is in the detection position, performing eye detection with the light irradiation parameter to obtain a corresponding fundus image. The method can avoid stray light interference and optimize fundus imaging.

Description

Technical Field

[0001] This application relates to the field of ophthalmic testing, and more particularly to an imaging method for a desktop fundus camera and a desktop fundus camera. Background Technology

[0002] Fundus examination is an important means of assessing eye health and plays a crucial role in the early diagnosis and monitoring of various eye diseases. With advancements in medical technology and increasing public awareness of health, the demand for high-quality, convenient fundus examinations is constantly growing. Desktop fundus cameras are widely used in medical institutions at all levels due to their ease of operation and small footprint.

[0003] Desktop fundus cameras typically employ digital imaging technology, combining optical systems and electronic sensors to acquire fundus images. These cameras generally include an illumination system to generate light of appropriate intensity and wavelength to illuminate the fundus; an imaging optical path to guide the reflected light from the fundus to the image sensor; and an image processing system to optimize and enhance the captured raw images. During use, the operator needs to adjust the camera's position and focus to ensure clear fundus images are obtained.

[0004] However, the imaging effect of the relevant desktop fundus camera is poor when there is stray light interference, which will affect the doctor's identification and judgment of subtle lesions. Summary of the Invention

[0005] This application provides an imaging method and a desktop fundus camera for avoiding stray light interference and optimizing fundus imaging.

[0006] In a first aspect, this application provides an imaging method for a desktop fundus camera, applied to a desktop fundus camera. The method includes: acquiring an eye image of a target object and determining the identity information of the target object based on the eye image; determining the eye parameters of the target object based on the identity information; determining the light illumination parameters and detection position during eye detection based on the eye parameters; detecting the eye position of the target object in real time; and when the eye position is determined to be at the detection position, performing eye detection using the light illumination parameters to obtain the corresponding fundus image.

[0007] In the above embodiments, the desktop fundus camera acquires images of the target object's eyes and determines its identity information, thereby determining eye parameters and illumination parameters. It detects the eye position in real time and performs detection at appropriate locations, enabling personalized fundus examinations based on each patient's individual characteristics. This improves image quality; by precisely controlling illumination parameters and detection positions, stray light interference is effectively avoided, resulting in clearer fundus images.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, when the eye position is determined to be at the detection position, eye detection is performed using light illumination parameters to obtain a corresponding fundus image. Specifically, this includes: when the eye position is determined to be at the detection position, emitting preset infrared light using light illumination parameters to obtain an infrared preview image; determining the eye focal length of the target object at the detection position based on the infrared preview image; and adjusting the operating parameters of the white light illumination module based on the light illumination parameters and the eye focal length, emitting white light using the operating parameters to obtain a fundus image.

[0009] In the above embodiments, the desktop fundus camera achieves precise fundus imaging by first emitting infrared light to acquire a preview image, and then adjusting the white light illumination parameters based on the preview image. Infrared preview not only reduces eye irritation but also helps determine the optimal eye focal length. Adjusting the white light illumination parameters based on this information ensures the acquisition of the best quality fundus images.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, determining the eye focal length of the target object at the detection position based on the infrared preview image specifically includes: determining whether the detection position meets the preset detection requirements based on the infrared preview image; if so, obtaining the positional relationship of the split reference line; the split reference line is illuminated according to the user settings based on the split-image focusing principle; adjusting the experimental focal length of the imaging optical path so that the positional relationship of the split reference line is aligned, and determining the eye focal length based on the corresponding experimental focal length.

[0011] In the above embodiments, the desktop fundus camera utilizes a split-image reference line and a split-image focusing principle to accurately determine the focal length of the eye, significantly improving image clarity and accuracy. By adjusting the experimental focal length of the imaging optical path to align the split-image reference line, the optimal focal length of the eye can be obtained. This improves focusing accuracy, reduces focusing time, and increases examination efficiency.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, determining the eye parameters of the target object based on identity information specifically includes: determining the target object's historical examination records based on identity information; extracting the target object's historical eye parameters from the most recent historical examination records; correcting the historical eye parameters based on the historical time, current time, and the target object's age information of the historical examination records to obtain the target object's eye parameters; the eye parameters include corneal curvature, axial length, pupil size, and refractive state.

[0013] In the above embodiments, the desktop fundus camera determines current ocular parameters by utilizing the patient's historical examination records and personal information, and corrects these parameters based on time intervals and age information, thus obtaining ocular parameters that more closely reflect the current condition. This improves the accuracy of the examination, reduces the need for repeated measurements, and increases examination efficiency.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, the light illumination parameters and detection position during eye detection are determined based on eye parameters, specifically including: constructing a virtual eyeball model based on the corneal curvature and axial length of the target object; simulating the propagation paths of light with different intensities, angles, and wavelengths in the virtual eyeball model to determine the target intensity, target angle, and target wavelength that meet preset illumination requirements; adjusting the aperture size of the illumination light to the target aperture range based on the pupil size of the target object, so that the imaging brightness of the virtual eyeball model meets a preset brightness threshold; integrating the target intensity, target angle, target wavelength, and target aperture range to obtain the light illumination parameters; determining the imaging plane position of the virtual eyeball model based on the refractive state of the target object; and determining the detection position of the target object's eye based on the imaging plane position.

[0015] In the above embodiments, the desktop fundus camera can more accurately predict the propagation of light in the eye by constructing a virtual eyeball model and simulating the light propagation path. By comprehensively considering multiple parameters to determine the optimal detection position, the accuracy of imaging is further improved.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, before the step of acquiring the eye image of the target object and determining the identity information of the target object based on the eye image, the method further includes: performing setting initialization in response to a user's self-test command; acquiring ambient light parameters after initialization is completed; and issuing an environment adjustment prompt message when the ambient light parameters do not meet the preset detection range.

[0017] In the above embodiments, the initialization of the desktop fundus camera settings can ensure that the device is in the best working condition, reduce errors caused by equipment factors, and issue timely adjustment prompts when the environment does not meet the requirements, ensuring that the examination is carried out under the best conditions and reducing repeated examinations caused by environmental factors.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, after determining that the eye position is at the detection position and performing eye detection with light illumination parameters to obtain the corresponding fundus image, the method further includes: performing image enhancement processing on the fundus image to obtain an optimized fundus image; identifying the optimized fundus image, determining potential lesion areas, and generating a preliminary diagnostic report based on the potential lesion areas; comparing the preliminary diagnostic report with the target object's historical diagnostic records to generate a disease change trend; and generating treatment suggestions and examination plans based on the disease change trend.

[0019] In the above embodiments, the desktop fundus camera improves image quality, automatically identifies potential lesion areas and generates preliminary diagnostic reports, which not only improves diagnostic efficiency but also provides doctors with valuable reference information. By comparing the current results with historical records, the trend of disease changes can be generated, which helps doctors to have a more comprehensive understanding of the patient's disease progression.

[0020] In a second aspect, embodiments of this application provide a desktop fundus camera, which includes one or more processors and a memory; the memory is coupled to the one or more processors and is used to store computer program code, which includes computer instructions, and the one or more processors call the computer instructions to cause the desktop fundus camera to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, embodiments of this application provide a computer program product containing instructions that, when the computer program product is run on a desktop fundus camera, cause the desktop fundus camera to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a desktop fundus camera, cause the desktop fundus camera to perform the method described in the first aspect and any possible implementation thereof.

[0023] Understandably, the desktop fundus camera provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of this application. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0025] 1. Because a method is used to acquire eye images of the target subject and determine their identity information, a unique identity can be established for each patient. Personalized parameters provide an important basis for subsequent lighting parameter settings and detection location determination. By detecting the eye position in real time, it is ensured that the examination is always performed in the best condition. Using optimized lighting parameters, high-quality fundus images are obtained.

[0026] 2. By employing a method that identifies the target individual's historical examination records based on their identity information and extracts historical ocular parameters from the most recent records, the system can fully utilize the patient's past data, avoiding the tedious process of remeasuring all parameters for each examination. By considering the time of the historical examination records, the current time, and the patient's age, the historical ocular parameters are corrected to obtain ocular parameters that better reflect the current condition, resulting in more accurate, efficient, and personalized fundus examinations.

[0027] 3. Because it adopts the method of setting and initializing in response to user self-test commands and obtaining ambient light parameters after initialization, it can ensure that the device is in the best working state before the examination begins and evaluate the examination environment. By obtaining ambient light parameters and comparing them with the preset detection range, it can issue adjustment prompts in a timely manner when the requirements are not met, ensuring that the examination is carried out under the best lighting conditions, and achieving more stable, reliable and standardized fundus examination. Attached Figure Description

[0028] Figure 1 This is a schematic flowchart of an imaging method using a desktop fundus camera in an embodiment of this application;

[0029] Figure 2 This is another schematic flowchart of the imaging method of the desktop fundus camera in the embodiments of this application;

[0030] Figure 3 This is a schematic diagram of the physical structure of a desktop fundus camera in an embodiment of this application. Detailed Implementation

[0031] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0032] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0033] The following describes the process of the method provided in this implementation. Please refer to [link / reference]. Figure 1This is a flowchart illustrating an imaging method using a desktop fundus camera in an embodiment of this application.

[0034] S101. Obtain the eye image of the target object and determine the identity information of the target object based on the eye image.

[0035] The target group refers to patients who require fundus examination. Eye images are digital images of the patient's eye area acquired through imaging equipment, including but not limited to images of the eye from the front, side, or specific features. Identification information serves as a unique identifier for the patient and may include personal information such as name, account number, and medical record number.

[0036] Specifically, the desktop fundus camera first activates its connected imaging device, such as a high-definition camera or a professional eye scanner, to capture a clear image of the patient's eyes. Then, the desktop fundus camera uses image recognition algorithms to analyze the image, extracting key features such as iris texture and corneal curvature. The camera compares these features with patient information stored in its database, finding the record with the highest match to identify the patient. If it is a first-time patient, the desktop fundus camera creates a new identity record.

[0037] In some embodiments, the acquisition of eye images and the determination of identity information of the target subject can be achieved in multiple ways: Optionally, a desktop fundus camera can use multispectral imaging technology to acquire eye images, including visible light, near-infrared, and far-infrared images, and then use deep learning algorithms to fuse these images to extract richer feature information; next, the desktop fundus camera uses biometric recognition algorithms, such as iris recognition or retinal vascular texture recognition, to match them with records in a database; finally, the desktop fundus camera combines the matching results with other auxiliary information (such as appointment records) to determine the patient's identity. Optionally, the desktop fundus camera can first request the patient to provide preliminary identity information, such as a name or part of an ID number; then, the desktop fundus camera uses a high-speed camera to capture dynamic image sequences of the patient blinking; next, the desktop fundus camera analyzes the eye movement features and eyelid texture in these image sequences as a basis for auxiliary identity recognition; finally, the desktop fundus camera integrates static and dynamic eye features to determine the patient's identity.

[0038] S102. Determine the eye parameters of the target object based on the identity information.

[0039] Ocular parameters refer to a series of numerical values ​​describing the physiological characteristics of a patient's eyes, used to represent various properties of the eyeball. These parameters typically include corneal curvature, axial length, pupil size, and refractive status. Corneal curvature indicates the degree of curvature of the corneal surface. Axial length is the distance from the anterior surface of the cornea to the retina. Pupil size refers to the diameter of the pupil. Refractive status is used to represent the optical characteristics of the eyeball, such as the degree of myopia, hyperopia, or astigmatism.

[0040] Specifically, the desktop fundus camera first accesses the electronic medical record database associated with the patient's identity information to retrieve the patient's historical examination records. The desktop fundus camera prioritizes retrieving the most recent eye examination data, including the specific values ​​of various eye parameters. Then, considering factors such as the patient's age and the date of the last examination, the desktop fundus camera uses a pre-set parameter evolution model to correct the historical data and estimate the current eye parameters. If the patient is undergoing their first examination or the historical data is incomplete, the desktop fundus camera will mark the parameters that need to be remeasured and notify the operator.

[0041] In some embodiments, the determination of the target object's ocular parameters can be achieved in several ways: Optionally, the desktop fundus camera can first retrieve the patient's complete historical examination records, including ocular parameter data from multiple examinations; then, the desktop fundus camera uses machine learning algorithms, such as time series analysis or regression analysis, to establish a personalized model of the patient's ocular parameters changing over time; next, the desktop fundus camera inputs factors such as the patient's age, occupation, and lifestyle into the model to predict the current ocular parameters; finally, the desktop fundus camera combines the prediction results with preset normal parameter ranges to determine the final ocular parameter values. Optionally, the desktop fundus camera can first retrieve patient ocular examination data from other medical institutions via remote connection; then, the desktop fundus camera uses a data fusion algorithm to integrate ocular parameter information from different sources; next, the desktop fundus camera applies methods such as weighted averaging or median filtering to eliminate possible data anomalies; finally, the desktop fundus camera determines the most suitable set of ocular parameters based on the integrated data and the current examination purpose.

[0042] S103. Based on eye parameters, determine the light illumination parameters and detection position during eye detection.

[0043] Among these, illumination parameters refer to a series of settings used to control the illumination source during fundus examination, including light intensity, wavelength, illumination angle, and duration; intensity indicates the brightness level of the light source; wavelength refers to the color characteristics of the light; illumination angle refers to the direction in which the light enters the eyeball; and duration indicates the length of each illumination session. Detection position indicates the optimal position of the camera or detection device relative to the patient's eyeball during fundus imaging.

[0044] Specifically, the desktop fundus camera first constructs a virtual eye model based on the patient's corneal curvature and axial length. Then, within this model, the camera simulates light propagation paths with different parameters, calculating the focusing and reflection intensity of light at the fundus. Based on the simulation results, the camera determines the combination of light parameters that yields the clearest fundus image. Simultaneously, considering the patient's pupil size and refractive state, the camera calculates the optimal detection position, including the distance and angle between the camera lens and the eyeball. The camera also adjusts parameters based on the patient's specific condition (such as cataracts) to ensure the safety and effectiveness of the examination.

[0045] S104. Real-time detection of the target object's eye position.

[0046] Among them, eye position refers to the specific position and orientation of the patient's eyeball in three-dimensional space, including the horizontal, vertical and front-back position relative to the detection device, as well as the rotation angle of the eyeball.

[0047] Specifically, the desktop fundus camera continuously performs this step throughout the fundus examination to ensure the patient's eye is always in optimal detection condition. The desktop fundus camera first activates the high-speed camera and distance sensor integrated with the fundus camera to capture a real-time image stream of the patient's eye, while the distance sensor measures the precise distance between the eye and the device. The desktop fundus camera uses computer vision algorithms to analyze this data, tracking the eye's movement trajectory and rotation angle. Simultaneously, the desktop fundus camera compares the detected eye position with the previously determined optimal detection position, calculating the deviation value. If the deviation exceeds a preset threshold, the desktop fundus camera will immediately adjust the position of the detection device or prompt the patient to adjust their posture until the deviation is within the preset threshold.

[0048] In some embodiments, real-time detection of the target object's eye position can be achieved in several ways: Optionally, a desktop fundus camera can first construct a structured light 3D scanning desktop fundus camera using multiple infrared LEDs and an infrared camera; then, the desktop fundus camera projects a specific pattern of infrared grating onto the patient's eye and captures the reflected image through the camera; next, the desktop fundus camera uses the principle of triangulation to reconstruct a 3D model of the eye based on the degree of grating deformation; finally, the desktop fundus camera accurately calculates the position and posture changes of the eyeball by comparing the changes in the 3D model between consecutive frames. Optionally, a desktop fundus camera can first deploy multiple miniature inertial measurement units (IMUs) at different parts of the examination device; then, the desktop fundus camera requires the patient to wear a lightweight eyeglass frame integrating the IMU; next, the desktop fundus camera simultaneously collects motion data of the device and the patient's head, and fuses this data using a Kalman filter algorithm; finally, the desktop fundus camera accurately derives the position change of the eyeball relative to the detection device by calculating the relative motion. It is understandable that other methods can be used to achieve real-time detection of the target object's eye position, such as using millimeter-wave radar technology for non-contact eye tracking or combining electrooculography (EOG) signals to analyze eye movements; this is not a limitation here.

[0049] S105. When the eye position is determined to be in the detection position, eye detection is performed using light illumination parameters to obtain the corresponding fundus image.

[0050] The detection position refers to the optimal imaging position determined in the previous steps, which is the ideal spatial position of the eyeball relative to the detection device. The illumination parameters refer to the optimal lighting settings determined in the previous steps, including intensity, wavelength, and angle. The fundus image refers to a high-resolution digital image of the retina and its blood vessels, optic nerve, and other structures acquired through a fundus camera.

[0051] Specifically, the desktop fundus camera controls the illumination to emit light of a specific intensity and wavelength based on pre-determined illumination parameters. Simultaneously, the desktop fundus camera activates the image acquisition device, including a high-resolution camera and a specialized optical system. The desktop fundus camera precisely controls the exposure time to complete image acquisition in the shortest possible time to reduce patient discomfort, for example, by using a white flash for image acquisition. After acquisition, the desktop fundus camera turns off the illumination and performs preliminary processing on the acquired raw image data, including noise reduction and contrast enhancement, ultimately generating high-quality fundus images.

[0052] The following provides a more detailed description of the process of the method provided in this implementation. Please refer to [link / reference]. Figure 2 This is another schematic diagram of the imaging method of the desktop fundus camera in the embodiments of this application.

[0053] S201. Obtain the eye image of the target object and determine the identity information of the target object based on the eye image.

[0054] Referring to step S101, the desktop fundus camera will determine the identity information of the target object.

[0055] In some embodiments, the desktop fundus camera responds to the user's self-test command and performs initialization settings; after initialization is complete, it acquires ambient light parameters; and when the ambient light parameters do not meet the preset detection range, it issues an environment adjustment prompt.

[0056] Among them, the self-test command refers to the user-triggered command for the device to perform a self-check. Setting initialization means restoring the device's various parameters to a predetermined standard state. Ambient light parameters refer to the characteristics of indoor light intensity, spectral distribution, etc., during the check. Preset detection range indicates the ambient light conditions required for the device to operate normally.

[0057] Specifically, the desktop fundus camera performs this process before starting a fundus examination to ensure the equipment is in optimal working condition and the environmental conditions are suitable for the examination. The desktop fundus camera first responds to the user's self-test command and initiates a comprehensive self-test program. This includes checking the functional status of various hardware modules, such as the light source, camera, and lens. The desktop fundus camera also calibrates various sensors to ensure data accuracy. After initialization, the desktop fundus camera activates the ambient light sensor to measure the light intensity and spectral distribution in the examination room. The desktop fundus camera compares the measured parameters with preset standard ranges. If the ambient light is found to be unsuitable, the desktop fundus camera will display a warning message on the screen and can provide voice prompts to guide the operator on how to adjust the indoor lighting, such as turning off certain light sources or drawing the curtains.

[0058] In some embodiments, device self-testing and environmental adjustment can be achieved in several ways: Optionally, the desktop fundus camera can first execute a series of preset test procedures, such as light source brightness testing, lens focusing testing, and sensor response testing; then, the desktop fundus camera analyzes the test results and generates a detailed status report; next, the desktop fundus camera automatically adjusts correctable parameters based on the status report, such as recalibrating color balance; finally, the desktop fundus camera provides the operator with a comprehensive report, including device status and any issues requiring manual intervention. Optionally, the desktop fundus camera can first use an integrated spectrometer to perform full-spectrum analysis of ambient light; then, the desktop fundus camera calculates the potential impact of ambient light on fundus imaging, such as reduced contrast or color distortion; next, the desktop fundus camera generates a virtual light compensation scheme to simulate an ideal examination environment; finally, the desktop fundus camera provides the operator with detailed environmental adjustment suggestions, including specific lighting settings and shading measures.

[0059] S202. Based on the identity information, determine the target's historical inspection records.

[0060] Among them, historical examination records refer to detailed information about the patient's past ophthalmological examinations at medical institutions, including the examination date, examination items, and examination results.

[0061] Specifically, the desktop fundus camera first accesses the hospital's electronic medical record database, using the patient's identity information as search keywords. The camera then queries multiple relevant data tables, including outpatient records, inpatient records, and examination reports. The search results are arranged chronologically, forming a complete historical examination timeline. The camera also checks for examination records from other medical institutions; if found, these external records are obtained through a secure data exchange protocol. Finally, the camera integrates all examination records into a unified data structure for easier subsequent processing and analysis.

[0062] In some embodiments, the determination of the target object's historical examination records can be achieved in several ways: Optionally, the desktop fundus camera can first perform a preliminary search in a central database using the patient's primary identification identifier (such as an ID card number); then, the desktop fundus camera uses a fuzzy matching algorithm to find records related to possible secondary identification identifiers (such as former names, old medical record numbers, etc.); next, the desktop fundus camera applies data mining technology to analyze all retrieved records, identifying and eliminating possible duplicate or erroneous information; finally, the desktop fundus camera uses machine learning algorithms to classify and sort the records, highlighting historical records related to ophthalmological examinations. Optionally, the desktop fundus camera can first establish a distributed query network connecting databases of multiple medical institutions; then, the desktop fundus camera initiates query requests in parallel within this network, simultaneously searching multiple data sources; next, the desktop fundus camera uses blockchain technology to ensure the security and traceability of cross-institutional data exchange; finally, the desktop fundus camera applies natural language processing technology to extract key examination information from unstructured medical record text.

[0063] S203. Extract the historical eye parameters of the target object from the most recent historical examination records.

[0064] Among them, historical ocular parameters refer to the ocular physiological indicators measured in past examinations, including but not limited to corneal curvature, axial length, pupil size, and refractive status.

[0065] Specifically, the desktop fundus camera first sorts historical examination records chronologically to determine the most recent one or more ophthalmological examinations. Then, it analyzes the structure of these records, identifying data fields containing ocular parameters. For standardized electronic records, the camera directly extracts values ​​from designated fields. For unstructured text records, it uses natural language processing to identify and extract relevant parameters. The camera also checks the completeness of parameters; if any parameters are missing, it marks them and considers using earlier records or other methods to supplement them. Finally, the camera formats the extracted historical ocular parameters into a standard format for subsequent processing.

[0066] In some embodiments, historical ocular parameters can be extracted in several ways: Optionally, the desktop fundus camera can first use Optical Character Recognition (OCR) technology to convert the scanned paper examination report into digital text; then, the desktop fundus camera applies a named entity recognition algorithm to identify various ocular parameters and their values ​​from the text; next, the desktop fundus camera uses a rule-based verification mechanism to check whether the extracted parameters are within a reasonable range; finally, the desktop fundus camera stores the verified parameters in a structured database and marks the data source and credibility. Optionally, the desktop fundus camera can first establish a dictionary of ophthalmic terminology and abbreviations; then, the desktop fundus camera uses this dictionary to perform semantic analysis on the examination records to identify keywords and phrases describing ocular parameters; next, the desktop fundus camera applies a contextual understanding algorithm to accurately match parameter names with their corresponding values; finally, the desktop fundus camera uses a data consistency check to compare parameter changes at different times and mark abnormal or suspicious data points.

[0067] S204. Based on the historical time, current time, and age information of the target object from the historical examination records, correct the historical eye parameters to obtain the eye parameters of the target object.

[0068] Here, "historical time" refers to the specific date of a past inspection. "Current time" indicates the date of this inspection. "Age information" indicates the actual age of the target individual.

[0069] Specifically, the desktop fundus camera first calculates the interval between the historical examination time and the current time. Then, it considers the subject's age and applies age-related parameter change models from ophthalmic research. For each ocular parameter, the desktop fundus camera uses a specific algorithm for correction. For example, for axial length, it can account for slight age-related increases; for corneal curvature, it can assume relative stability; for pupil size, it can consider age-related shrinkage trends; and for refractive status, it can consider myopia progression or presbyopia development based on age. The desktop fundus camera also considers the patient's medical history, such as cataract surgery, which can significantly alter certain parameters. Finally, the desktop fundus camera generates a set of corrected ocular parameters as initial estimates for the current examination.

[0070] In some embodiments, ocular parameters can be corrected in several ways: Optionally, the desktop fundus camera can first establish an age-related change model of ocular parameters based on artificial population data; then, the desktop fundus camera inputs the target subject's historical data into this model to generate a personalized parameter change prediction curve; next, the desktop fundus camera considers factors such as the target subject's lifestyle and occupation to fine-tune the prediction curve; finally, the desktop fundus camera calculates the estimated ocular parameters at the current time point based on the adjusted curve. Optionally, the desktop fundus camera can first use machine learning algorithms to analyze longitudinal data from a large number of patients to establish a prediction model of ocular parameters changing over time; then, the desktop fundus camera inputs the target subject's historical parameters, age, and time intervals into this model; next, the desktop fundus camera generates multiple possible parameter change scenarios and calculates the probability of each scenario; finally, the desktop fundus camera selects the scenario with the highest probability, or combines multiple high-probability scenarios, to obtain the corrected ocular parameters. It is understandable that other methods can be used to correct eye parameters, such as using a personalized eye development model based on genetic information, or dynamically adjusting parameters by combining real-time collected physiological data; no specific method is specified here.

[0071] S205. Based on eye parameters, determine the light illumination parameters and detection position during eye detection.

[0072] Referring to step S103, the desktop fundus camera will determine the light illumination parameters and detection location.

[0073] In some embodiments, the desktop fundus camera constructs a virtual eye model based on the corneal curvature and axial length of the target object; it simulates the propagation paths of light with different intensities, angles, and wavelengths in the virtual eye model to determine the target intensity, target angle, and target wavelength that meet preset illumination requirements; it adjusts the aperture size of the irradiated light to the target aperture range based on the pupil size of the target object, so that the imaging brightness of the virtual eye model meets a preset brightness threshold; it integrates the target intensity, target angle, target wavelength, and target aperture range to obtain the light illumination parameters; it determines the imaging plane position of the virtual eye model based on the refractive state of the target object; and it determines the detection position of the target object's eye based on the imaging plane position.

[0074] The virtual eye model refers to a digital eye structure constructed based on the patient's eye parameters. Preset illumination requirements refer to the lighting conditions set to obtain high-quality fundus images. The target aperture range represents the optimal area for light illumination. The preset brightness threshold refers to the ideal brightness level during imaging.

[0075] Specifically, the desktop fundus camera performs this process after acquiring the patient's eye parameters, optimizing lighting parameters and determining the detection position for fundus examination. First, the desktop fundus camera uses the patient's corneal curvature and axial length data to construct a precise three-dimensional eye model in a computer. Then, the desktop fundus camera simulates light propagation with different parameters in this virtual model, including various combinations of intensities, incident angles, and wavelengths. The desktop fundus camera evaluates the imaging effect of each combination and selects the optimal parameters that meet preset standards. Next, the desktop fundus camera considers the patient's pupil size and adjusts the aperture range to ensure sufficient light enters the eye while avoiding overstimulation. The desktop fundus camera integrates these optimized parameters to form the final lighting scheme. Finally, based on the patient's refractive state, the desktop fundus camera determines the optimal imaging plane position in the virtual model and calculates the ideal position of the eyeball relative to the device during the actual examination.

[0076] In some embodiments, the construction of a virtual eye model and the optimization of light parameters can be achieved in several ways: Optionally, the desktop fundus camera can first use the finite element analysis method to create a multi-layered eye model including the cornea, lens, vitreous body, and retina; then, the desktop fundus camera applies a ray tracing algorithm to simulate the propagation paths of a large number of light rays in the model; next, the desktop fundus camera uses a genetic algorithm to optimize the light parameters, finding the optimal illumination scheme through multiple generations of iteration; finally, the desktop fundus camera conducts virtual imaging experiments to verify the actual effect of the optimized parameters. Optionally, the desktop fundus camera can first establish a template library containing multiple eye types based on big data analysis; then, the desktop fundus camera selects the basic template that is closest to the patient's parameters and makes personalized adjustments; next, the desktop fundus camera uses the Monte Carlo method to randomly generate a large number of light parameter combinations and evaluate the imaging quality of each combination; finally, the desktop fundus camera applies a machine learning algorithm to learn the optimal parameter selection strategy from massive simulation results. It is understandable that other methods can be used to construct virtual eyeball models and optimize lighting parameters, such as using deep reinforcement learning techniques to dynamically adjust lighting parameters, or combining real-time eye tracking technology to achieve adaptive lighting control, which is not limited here.

[0077] S206. Real-time detection of the target object's eye position.

[0078] Referring to step S104, the desktop fundus camera will detect the position of the eye in real time.

[0079] S207. When the eye position is determined to be in the detection position, emit preset infrared light with light illumination parameters to obtain an infrared preview image.

[0080] Infrared light refers to light with wavelengths in the near-infrared region (typically 700-1000 nanometers), used for non-invasive observation of eye structures. Infrared preview images are images of eye structures obtained after illumination with infrared light.

[0081] Specifically, the desktop fundus camera first verifies the stability of the eye's position, ensuring it is within acceptable limits. Then, based on previously determined illumination parameters, the desktop fundus camera adjusts the infrared light source settings. It activates the infrared emitter, emitting infrared light of a preset wavelength and intensity. Simultaneously, the desktop fundus camera activates a dedicated infrared sensor or changes the mode of a regular camera to receive infrared light. The desktop fundus camera controls the exposure time, typically longer than visible light imaging, to acquire sufficient signal. Finally, the desktop fundus camera processes the received infrared signal, generating a clear infrared preview image. This image typically reveals deep eye structures, such as iris texture and some retinal features.

[0082] In some embodiments, infrared preview images can be acquired in various ways: Optionally, a desktop fundus camera can first use multi-wavelength near-infrared light sources, such as 850nm and 940nm; then, the desktop fundus camera emits these different wavelengths of infrared light in a rapid, alternating manner; next, the desktop fundus camera uses synchronous acquisition technology to capture images at different wavelengths separately; finally, the desktop fundus camera applies an image fusion algorithm to synthesize the images of multiple wavelengths into a more informative infrared preview image. Optionally, the desktop fundus camera can first use structured light technology to project a specific pattern of infrared grating onto the eye; then, the desktop fundus camera uses a high-speed camera to capture the reflected grating pattern; next, the desktop fundus camera reconstructs the three-dimensional structure of the eye by analyzing grating deformation; finally, the desktop fundus camera combines the three-dimensional information with the two-dimensional infrared image to generate an enhanced infrared preview image containing depth information. It is understood that other methods can also be used to acquire infrared preview images, such as using adaptive optics technology to compensate for optical distortions in the eye in real time, or combining eye-tracking technology for dynamic infrared imaging, which are not limited here.

[0083] S208. Based on the infrared preview image, determine the eye focal length of the target object at the detection position.

[0084] Among them, the focal length of the eye represents the distance from the anterior surface of the cornea to the imaging plane inside the eyeball, and is an important parameter for adjusting the examination equipment.

[0085] The desktop fundus camera performs this step after acquiring the infrared preview image, preparing for subsequent white light imaging. Specifically, the desktop fundus camera first preprocesses the infrared preview image, including noise reduction and contrast enhancement. Then, it uses image analysis algorithms to identify key structures in the image, such as corneal reflection, lens edge, and retinal surface. The desktop fundus camera calculates the relative positions and sharpness of these structures. Next, it applies an optical model to map the features in the image to the actual eye structure. The desktop fundus camera can use multiple consecutively captured infrared images, determining the optimal focal length by comparing the sharpness of different focal planes. Finally, the desktop fundus camera outputs a precise eye focal length value, which will be used to adjust the parameters for illuminating the desktop fundus camera with white light and for imaging the image.

[0086] In some embodiments, the eye focal length can be determined in several ways: Optionally, the desktop fundus camera can first use an edge detection algorithm to identify clear structural edges in the infrared preview image; then, the desktop fundus camera applies Fourier transform to analyze the frequency domain features of the image; next, the desktop fundus camera compares the high-frequency components of different depth planes to find the clearest imaging plane; finally, the desktop fundus camera converts the clearest plane into the actual eye focal length according to the parameters of the optical system. Optionally, the desktop fundus camera can first use a deep learning model, such as a convolutional neural network, to extract features from the infrared preview image; then, the desktop fundus camera compares the extracted features with a large number of pre-labeled samples; next, the desktop fundus camera uses regression analysis to estimate the eye focal length based on feature similarity; finally, the desktop fundus camera accurately determines the optimal focal length through small-range focus fine-tuning and image quality assessment. It is understandable that other methods can be used to determine the focal length of the eye, such as using phase detection autofocus technology, or combining optical coherence tomography (OCT) technology for precise measurement of the eye structure, which is not limited here.

[0087] In some embodiments, the desktop fundus camera determines whether the detection position meets the preset detection requirements based on the infrared preview image; if so, it obtains the positional relationship of the split reference line; the split reference line is illuminated according to the user settings based on the split-image focusing principle; the experimental focal length of the imaging optical path is adjusted so that the positional relationship of the split reference line is aligned, and the focal length of the eye is determined based on the corresponding experimental focal length.

[0088] Among these, the preset detection requirements represent the standard requirements for image quality and eye position. The split reference line refers to a special light pattern used for precise focusing. The imaging optical path refers to the path of light from the eyeball to the image sensor. The experimental focal length represents the focal length value adjusted during focusing. The eye focal length refers to the final determined focal length that yields a clear image of the fundus.

[0089] Specifically, the desktop fundus camera first analyzes the infrared preview image to assess whether the image quality and eye position meet preset detection standards. If the conditions are met, the desktop fundus camera activates the split reference line projection device. This device projects a specific pattern of light onto the eye according to the operator's settings. The desktop fundus camera then begins adjusting the focal length of the imaging optical path. During this process, the image of the split reference lines will exhibit different states of separation or overlap. The desktop fundus camera captures these changes using a high-speed camera and uses image processing algorithms to analyze the positional relationship of the reference lines in real time. When the desktop fundus camera detects that the reference lines are perfectly aligned, it records the current focal length value. Finally, the desktop fundus camera can fine-tune around this focal length to ensure the optimal focal length for the eye.

[0090] It's important to note that split-image focusing is based on a combination of beam splitters and prisms in the optical system. This technique splits the incident light beam into two parts, and then uses special optical elements to cause these two beams to shift relative to each other. When the observed object (in this case, the fundus) is at the focal point, the two beams will precisely overlap on the image plane; if they are not at the focal point, a misaligned or separated image will appear. The specific working principle is as follows:

[0091] Beam splitting: The incident beam first passes through a beam splitter, which divides the light into two equal parts;

[0092] Beam deflection: One beam of light passes through a specially designed prism or lens system, causing it to shift laterally;

[0093] Image formation: After passing through the main imaging optical system, two beams of light form two adjacent or partially overlapping images on the image plane;

[0094] Focus judgment: When the observed object is in focus, the two images will be precisely aligned to form a complete and clear image; if the object is not in focus, the two images will be misaligned, forming a split image;

[0095] Focus adjustment: By observing the degree and direction of the split image, the direction and magnitude of the focus shift can be determined, thereby guiding the adjustment of the focus.

[0096] When used in a desktop fundus camera, the system automatically analyzes the state of the split image. Specifically, the desktop fundus camera quickly captures a series of split image images at different focal lengths. Image processing algorithms analyze the alignment of the split images in each image, then identify the focal length at which the split images are perfectly aligned – the optimal focal length. Finally, a small-scale scan is performed near the optimal focal length to obtain more precise focusing results. During the examination, the desktop fundus camera continuously monitors the split image state and adjusts the focal length in real time to accommodate any minor movements the patient may make.

[0097] S209. Based on the light illumination parameters and the eye focal length, adjust the operating parameters of the white light illumination module and emit white light according to the operating parameters to obtain a fundus image.

[0098] The white light illumination module refers to the device component that generates light within the visible spectrum. Operating parameters refer to the specific settings that control the operation of the white light illumination module, such as current intensity, spectral distribution, and pulse frequency. Fundus images are clear images of the retina and its blood vessels, optic nerve, and other structures obtained by illuminating it with white light.

[0099] After determining the focal length of the eye, the desktop fundus camera performs this step to obtain the final fundus image. Specifically, the desktop fundus camera first inputs the previously determined illumination parameters and the calculated focal length of the eye into its control module. Then, based on these inputs, the desktop fundus camera calculates the optimal operating parameters for the white light illumination module, including the current intensity, color temperature, and illumination time of the light source. The desktop fundus camera can fine-tune the spectral distribution to highlight certain fundus structures. Next, the desktop fundus camera activates the white light illumination module, precisely controlling the emission of white light. Simultaneously, the desktop fundus camera adjusts the image sensor settings, such as sensitivity and exposure time, to match the white light illumination. The desktop fundus camera completes image acquisition in a very short time to reduce patient discomfort and avoid blurring caused by eye movement. Finally, the desktop fundus camera rapidly processes the acquired raw image data, including noise reduction, color correction, and sharpening, to generate a high-quality fundus image.

[0100] In some embodiments, fundus images can be acquired in multiple ways: Optionally, a desktop fundus camera can first use a tunable narrowband light source to rapidly switch between different wavelengths of light according to a preset sequence; then, the desktop fundus camera synchronously adjusts the image sensor to optimize the acquisition parameters for each wavelength; next, the desktop fundus camera completes image acquisition for multiple wavelengths in a very short time; finally, the desktop fundus camera uses a multispectral image fusion algorithm to synthesize the images of different wavelengths into an information-rich color fundus image. Optionally, the desktop fundus camera can first employ scanning laser fundus photography technology using a low-power white light laser; then, the desktop fundus camera controls the laser to perform high-speed two-dimensional scanning, illuminating the retina point by point; next, the desktop fundus camera uses a high-sensitivity photomultiplier tube to receive the reflected light signal; finally, the desktop fundus camera uses a real-time image reconstruction algorithm to convert the scanned data into a high-resolution fundus image. It is understood that other methods can also be used to acquire fundus images, such as using adaptive optics technology to compensate for optical distortions of the eyeball in real time, or combining fundus autofluorescence imaging technology to enhance the display of specific tissues; these are not limited here.

[0101] In some embodiments, the desktop fundus camera performs image enhancement processing on the fundus image to obtain an optimized fundus image; identifies the optimized fundus image, determines potential lesion areas, and generates a preliminary diagnostic report based on the potential lesion areas; compares the preliminary diagnostic report with the target subject's historical diagnostic records to generate a trend of disease progression; and generates treatment recommendations and examination plans based on the trend of disease progression.

[0102] Image enhancement processing refers to the process of improving image quality through various algorithms. Optimized fundus image represents a clearer, higher-contrast fundus image after processing. Potential lesion area refers to fundus areas with pathological changes. Preliminary diagnostic report is a preliminary medical assessment generated by the desktop fundus camera based on image analysis. Historical diagnostic record refers to the patient's past ophthalmological examination results. Disease trend indicates how the patient's fundus condition changes over time. Treatment recommendation is the treatment plan provided by the desktop fundus camera. Examination plan refers to the schedule for future fundus examinations.

[0103] The desktop fundus camera performs this process after acquiring fundus images, providing comprehensive diagnostic assistance information. Specifically, the desktop fundus camera first applies a series of enhancement algorithms to the raw fundus images, such as noise reduction, sharpening, and contrast adjustment, to generate optimized images that are easier to analyze. Then, the desktop fundus camera uses computer vision and machine learning algorithms to identify various structures in the image, such as blood vessels and optic discs, and marks abnormal areas. Based on these findings, the desktop fundus camera generates a preliminary diagnostic report containing a description of potential lesions. Next, the desktop fundus camera accesses the patient's electronic medical record, extracts historical diagnostic records, and compares and analyzes them with the current results. The desktop fundus camera generates trend charts reflecting changes in the condition through time-series analysis. Finally, based on the changing trends and current condition, the desktop fundus camera uses pre-set clinical guidelines to generate personalized treatment recommendations and follow-up examination plans.

[0104] In some embodiments, post-processing and diagnostic assistance of fundus images can be achieved in multiple ways: Optionally, the desktop fundus camera can first use a deep learning network, such as U-Net, to perform semantic segmentation on the fundus image and accurately identify various fundus structures; then, the desktop fundus camera applies anomaly detection algorithms, such as isolated forest, to identify potential lesion areas; next, the desktop fundus camera uses natural language processing technology to transform the image analysis results into structured diagnostic descriptions; finally, the desktop fundus camera uses knowledge graph technology to integrate patient historical data and the latest research results to generate personalized treatment recommendations. Optionally, the desktop fundus camera can first employ multi-scale image analysis technology to detect fundus abnormalities at different resolutions; then, the desktop fundus camera uses a time series prediction model, such as an LSTM network, to analyze the patient's disease progression trend; next, the desktop fundus camera applies decision support algorithms, such as Bayesian networks, to evaluate the potential effects of different treatment options; finally, the desktop fundus camera uses a multi-objective optimization algorithm to comprehensively consider treatment effects, side effects, and individual patient factors to formulate the optimal treatment and follow-up plan. It is understandable that other methods can be used to achieve post-processing and diagnostic assistance of fundus images, such as using federated learning technology to integrate the diagnostic experience of multiple hospitals, or combining genomic data for personalized risk assessment, which is not limited here.

[0105] In this embodiment, by employing technologies such as patient identification, historical data analysis, real-time ophthalmic examination, and adaptive light control, the examination parameters can be automatically adjusted according to the unique characteristics of each patient. This effectively solves the problems of inflexible parameter settings, low examination efficiency, and poor patient experience associated with traditional fundus cameras when dealing with different patients. Consequently, it achieves personalized, efficient, and humanized fundus examinations, improving patient comfort, especially for special groups such as the elderly and children. Simultaneously, through image analysis and diagnostic assistance functions, it provides doctors with more comprehensive and objective diagnostic information, helping to improve the early diagnosis rate and treatment effectiveness of ophthalmic diseases.

[0106] The desktop fundus camera in the embodiments of this invention is described below from the perspective of hardware processing. Please refer to [link / reference]. Figure 3 This is a schematic diagram of the physical structure of a desktop fundus camera in an embodiment of this application.

[0107] It should be noted that, Figure 3 The structure of the desktop fundus camera shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0108] like Figure 3 As shown, the desktop fundus camera includes a Central Processing Unit (CPU) 301, which can perform various appropriate actions and processes based on a program stored in Read-Only Memory (ROM) 302 or a program loaded from storage portion 308 into Random Access Memory (RAM) 303, such as performing the methods described in the above embodiments. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An Input / Output (I / O) interface 305 is also connected to the bus 304.

[0109] The following components are connected to I / O interface 305: input section 306 including audio input devices, push-button switches, etc.; output section 307 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 308 including a hard disk, etc.; and communication section 309 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0110] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs the various functions defined in the present invention.

[0111] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0112] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0113] Specifically, the desktop fundus camera of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the imaging method of the desktop fundus camera provided in the above embodiment.

[0114] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the desktop fundus camera described in the above embodiments; or it may exist independently and not assembled into the desktop fundus camera. The storage medium carries one or more computer programs that, when executed by a processor of the desktop fundus camera, cause the desktop fundus camera to implement the imaging method of the desktop fundus camera provided in the above embodiments.

[0115] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0116] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0117] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. An imaging method for a desktop fundus camera, characterized in that, Applied to a desktop fundus camera, the method includes: Obtain an image of the target object's eyes, and determine the target object's identity information based on the eye image; Based on the identity information, determine the eye parameters of the target object; specifically, determining the eye parameters of the target object based on the identity information includes: determining the target object's historical examination records based on the identity information; extracting the target object's historical eye parameters from the most recent historical examination records; correcting the historical eye parameters based on the historical time, current time, and the target object's age information of the historical examination records to obtain the target object's eye parameters; the eye parameters include corneal curvature, axial length, pupil size, and refractive state; Based on the aforementioned eye parameters, the light illumination parameters and detection position during eye detection are determined. Specifically, determining the light illumination parameters and detection position based on the aforementioned eye parameters includes: constructing a virtual eyeball model based on the corneal curvature and axial length of the target object; simulating the propagation paths of light with different intensities, angles, and wavelengths in the virtual eyeball model to determine the target intensity, target angle, and target wavelength that meet preset illumination requirements; adjusting the aperture size of the illuminating light to the target aperture range based on the pupil size of the target object, so that the imaging brightness of the virtual eyeball model meets a preset brightness threshold; integrating the target intensity, target angle, target wavelength, and target aperture range to obtain the light illumination parameters; determining the imaging plane position of the virtual eyeball model based on the refractive state of the target object; and determining the detection position of the target object's eye based on the imaging plane position. Real-time detection of the target object's eye position; When the eye position is determined to be at the detection position, eye detection is performed using the light illumination parameters to obtain the corresponding fundus image.

2. The method according to claim 1, characterized in that, When the eye position is determined to be at the detection position, eye detection is performed using the light illumination parameters to obtain a corresponding fundus image, specifically including: When the eye position is determined to be at the detection position, preset infrared light is emitted with the light illumination parameters to obtain an infrared preview image; Based on the infrared preview image, determine the eye focal length of the target object at the detection location; Based on the light illumination parameters and the eye focal length, the operating parameters of the white light illumination module are adjusted and white light is emitted according to the operating parameters to obtain a fundus image.

3. The method according to claim 2, characterized in that, The step of determining the eye focal length of the target object at the detection position based on the infrared preview image specifically includes: Based on the infrared preview image, determine whether the detection location meets the preset detection requirements; If so, the positional relationship of the splitting reference line is obtained; the splitting reference line is based on the split-image focusing principle and is illuminated according to user settings; The experimental focal length of the imaging optical path is adjusted so that the positional relationship of the split reference lines is aligned, and the eye focal length is determined based on the corresponding experimental focal length.

4. The method according to claim 1, characterized in that, Before the step of acquiring the eye image of the target object and determining the identity information of the target object based on the eye image, the method further includes: In response to the user's self-test command, perform configuration initialization; After initialization is complete, obtain the ambient light parameters; When the ambient light parameters do not meet the preset detection range, an environmental adjustment prompt message is issued.

5. The method according to claim 1, characterized in that, After determining that the eye position is at the detection position, and performing eye detection using the light illumination parameters to obtain the corresponding fundus image, the method further includes: The fundus image is subjected to image enhancement processing to obtain an optimized fundus image; The optimized fundus image is identified to determine potential lesion areas, and a preliminary diagnostic report is generated based on the potential lesion areas. The preliminary diagnosis report is compared with the target subject's historical diagnosis records to generate a trend of disease progression. Based on the described trend of disease progression, treatment recommendations and examination plans are generated.

6. A desktop fundus camera, characterized in that, The desktop fundus camera includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the desktop fundus camera to perform the method as described in any one of claims 1-5.

7. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on a desktop fundus camera, the desktop fundus camera performs the method as described in any one of claims 1-5.

8. A computer program product, characterized in that, When the computer program product is run on a desktop fundus camera, the desktop fundus camera performs the method as described in any one of claims 1-5.

Images