An imaging method for a fundus camera and a portable fundus camera

Abstract

An imaging method and a portable fundus camera for a fundus camera, which relate to the field of ophthalmic detection. The method includes: collecting an eye image of a target object and determining the identity information of the target object according to the eye image; obtaining the historical detection data of the target object according to the identity information; when it is determined that the eyes of the target object are in a preset detection action according to the eye image, obtaining an infrared preview image; determining a first focal length of the target object under infrared light irradiation according to the infrared preview image; determining a second focal length of the target object under white light irradiation according to the first focal length and the historical detection data; and obtaining a fundus image of the target object with the second focal length as the focusing setting information. Implementing this method can improve the focusing and image acquisition efficiency of the fundus camera.

Description

Technical Field

[0001] This application relates to the field of ophthalmic detection, and particularly to an imaging method for a fundus camera and a portable fundus camera. Background Art

[0002] Fundus examination is an indispensable and important means in ophthalmic diagnosis. It can directly observe fundus structures such as the retina, optic disc, macula, and retinal blood vessels, providing key information for the diagnosis of various eye diseases. With the continuous progress of medical technology, the fundus camera, as a non-invasive examination tool, has been widely used in ophthalmic clinical practice. High-quality and high-efficiency fundus images not only help doctors make accurate diagnoses but also provide important basis for the tracking and management of patients' conditions.

[0003] Currently, the commonly used imaging method for fundus cameras mainly adopts digital imaging technology. During the imaging process, the operator first adjusts the position and focal length of the camera to align it with the patient's pupil. Then, the fundus is illuminated by the camera's light source, and at the same time, the reflected light is captured by a digital sensor. The captured image is then digitally processed to finally form a fundus image for doctors to diagnose.

[0004] However, the related technology requires a long time for focusing and image acquisition, with low detection efficiency, resulting in eye fatigue of the patient and affecting the image quality of the imaging. Summary of the Invention

[0005] This application provides an imaging method for a fundus camera and a portable fundus camera, which are used to improve the focusing and image acquisition efficiency of the fundus camera.

[0006] In a first aspect, this application provides an imaging method for a fundus camera, which is applied to a fundus camera. The method includes: collecting an eye image of a target object and determining the identity information of the target object according to the eye image; obtaining the historical detection data of the target object according to the identity information; when it is determined that the eyes of the target object are in a preset detection action according to the eye image, obtaining an infrared preview image; determining a first focal length of the target object under infrared light irradiation according to the infrared preview image; determining a second focal length of the target object under white light irradiation according to the first focal length and the historical detection data; and obtaining a fundus image of the target object with the second focal length as the focusing setting information.

[0007] In the above embodiment, the fundus camera can obtain historical detection data according to the identity information of the target object, and predict the second focal length under white light irradiation by combining the first focal length determined by the infrared preview image. Based on historical data and infrared preview for focal length prediction, the focusing time during white light imaging is shortened, and the acquisition efficiency of fundus images is improved. At the same time, since the white light irradiation time is reduced, the stimulation to the eyes of the subject is also reduced, and the comfort of the subject is improved.

[0008] In some embodiments in combination with some embodiments of the first aspect, there are multiple infrared preview images, and each infrared preview image corresponds to a focal length position; determining a first focal length of a target object under infrared light irradiation according to the infrared preview images specifically includes: extracting edge features of the infrared preview images, and determining corresponding clarity evaluation indexes according to the edge features; when the clarity evaluation index reaches a preset clarity threshold, recording the corresponding target focal length position; and calculating the first focal length according to the optical system parameters of the fundus camera and the target focal length position.

[0009] In the above embodiments, when the fundus camera acquires infrared preview images, by analyzing the edge features and clarity of the images at multiple focal length positions, the best target focal length position is selected, and the first focal length is calculated in combination with the optical system parameters. Through multiple sampling analyses, the accuracy of focal length determination in the infrared preview stage is improved.

[0010] In some embodiments in combination with some embodiments of the first aspect, determining a second focal length of the target object under white light irradiation according to the first focal length and historical detection data specifically includes: extracting multiple detection records of the target object from the historical detection data; the detection records include the infrared focal length of the target object under infrared light, the white light focal length under white light, and the historical diopter at the time of detection; calculating the focusing deviation value between the infrared focal length and the white light focal length; establishing a deviation prediction model according to the focusing deviation value and the corresponding historical diopter; inputting the first focal length and the current diopter of the target object into the deviation prediction model to obtain a predicted deviation value; and calculating the second focal length according to the first focal length and the predicted deviation value.

[0011] In the above embodiments, the fundus camera uses the infrared focal length, white light focal length, and diopter information in the historical detection data to establish a deviation prediction model, and can accurately predict the deviation value of the white light focal length according to the current infrared focal length and the diopter of the target object, making use of individualized historical information and improving the accuracy of white light focal length prediction.

[0012] In some embodiments in combination with some embodiments of the first aspect, after the step of obtaining the fundus image of the target object with the second focal length as the focusing setting information, the method further includes: identifying the overexposed area and underexposed area in the fundus image; using a tone mapping algorithm to process the overexposed area and underexposed area respectively to obtain a tone-optimized area; and restoring the tone-optimized area to the fundus image to obtain an optimized fundus image.

[0013] In the above embodiments, after the fundus camera acquires a fundus image, by identifying overexposed and underexposed regions and performing optimization processing using a tone mapping algorithm, the overall quality of the fundus image is effectively improved. By balancing the brightness and contrast of different regions, the fundus structure becomes clearer, facilitating accurate diagnosis by doctors.

[0014] Combined with some embodiments of the first aspect, in some embodiments, identifying overexposed regions and underexposed regions in a fundus image specifically includes: determining the HSV color space corresponding to the fundus image; calculating the distribution histogram of the pixel values of the V channel in the HSV color space; determining a high brightness threshold and a low brightness threshold according to the distribution histogram; identifying the region where the pixel value of the V channel is higher than the high brightness threshold as an overexposed region; and identifying the region where the pixel value of the V channel is lower than the low brightness threshold as an underexposed region.

[0015] In the above embodiments, the fundus camera uses the distribution of the pixel values of the V channel in the HSV color space to determine the high and low brightness thresholds, achieving precise identification of abnormally exposed regions. Analyzing based on the color space is more sensitive and reliable than the traditional gray threshold method and can adapt to fundus images under different lighting conditions.

[0016] Combined with some embodiments of the first aspect, in some embodiments, before the step of acquiring an infrared preview image when it is determined that the eyes of the target object are in a preset detection action according to the eye image, the method further includes: acquiring left and right mirror eye images captured by the binocular camera module of the fundus camera; calculating the initial distance between the eyes of the target object and the binocular camera module according to the image deviation positions of the preset reference objects in the left and right mirror eye images; and determining the initial focal length of the target object during infrared preview according to the initial distance.

[0017] In the above embodiments, the fundus camera uses the binocular camera module to acquire left and right mirror eye images, calculates the initial distance between the eyes of the target object and the camera by analyzing the image deviation positions of the reference objects, and determines the initial focal length setting for the infrared preview stage through stereo vision ranging, shortening the focusing time.

[0018] Combined with some embodiments of the first aspect, in some embodiments, after the step of acquiring a fundus image of the target object with the second focal length as the focus adjustment setting information, the method further includes: performing feature analysis on the fundus structure in the fundus image to obtain a lesion detection result; determining the pathological evolution indication of the lesion detection result in combination with historical detection data; and generating a detection report according to the pathological evolution indication.

[0019] In the above embodiments, after the fundus camera acquires a fundus image, it analyzes the features of the fundus structure and combines historical detection data to generate a detection report containing pathological evolution indications, improving the doctor's diagnosis efficiency and facilitating the long-term tracking and management of diseases.

[0020] In a second aspect, an embodiment of the present application provides a fundus camera, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, and the computer program code includes computer instructions. The one or more processors call the computer instructions to cause the fundus camera to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product containing instructions. When the computer program product runs on a fundus camera, it causes the fundus camera to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, including instructions. When the instructions run on a fundus camera, it causes the fundus camera to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0023] It can be understood that the 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 method provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be elaborated here.

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

[0025] 1. Since a focal length prediction method based on historical data and infrared preview is adopted, the optimal focal length under white light illumination can be determined quickly and accurately, effectively solving the problems of long focusing time and low efficiency in white light imaging in the prior art. By obtaining the identity information and historical detection data of the target object, the fundus camera establishes an individualized focal length prediction basis, and uses the corresponding relationship between the infrared focal length and the white light focal length in the historical data for focal length calculation, improving the detection efficiency and accuracy.

[0026] 2. Since an exposure anomaly region recognition method based on the HSV color space and a tone mapping optimization algorithm are adopted, the uneven exposure problem in the fundus image can be accurately located and improved, effectively solving the problems of unstable fundus image quality and local detail loss in the prior art, and thus realizing the output of high-quality and information-rich fundus images.

[0027] 3. Since the initial distance measurement and initial focal length setting method based on binocular cameras are adopted, the appropriate starting focal length can be quickly determined in the infrared preview stage, effectively solving the problem of blind and time-consuming initial focusing in the prior art. Furthermore, a faster and more accurate fundus image acquisition process is achieved. By simultaneously capturing eye images with the left and right lenses and using the parallax principle to calculate the precise distance between the eye and the camera, it is applicable to various inspection scenarios, thus improving the adaptability of the application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a schematic flowchart of an imaging method of a fundus camera in an embodiment of the present application;

[0029] Figure 2 is another schematic flowchart of an imaging method of a fundus camera in an embodiment of the present application;

[0030] Figure 3 is a schematic structural diagram of a physical device of a fundus camera in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application, the singular forms "a", "an", "the above", "the", and "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations including one or more of the listed items.

[0032] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0033] Please refer to Figure 1 , which is a schematic flowchart of an imaging method of a fundus camera in an embodiment of the present application.

[0034] S101. Capture an eye image of a target object and determine the identity information of the target object according to the eye image.

[0035] Among them, the target object represents a patient or subject who needs to undergo fundus examination. The eye image refers to a digital image containing the eye region of the target object obtained through the front camera of a fundus camera or other image acquisition devices. The identity information is used to represent the personal identification information of the target object, such as name, ID number, or other unique identifiers.

[0036] Specifically, when the target object sits in front of the fundus camera and is ready for examination, the fundus camera will activate the image acquisition module. The fundus camera first acquires the eye image of the target object, including the entire face or a partial eye region. Then the fundus camera will use image processing and face recognition technologies to analyze the obtained eye image and extract key features such as iris texture and corneal shape. The fundus camera will compare these features with the pre-stored patient database to determine the identity information of the target object.

[0037] S102. Obtain the historical detection data of the target object according to the identity information.

[0038] Among them, the historical detection data refers to various relevant data records generated during the previous fundus examinations of the target object, including previous fundus images, diagnosis results, medication records, vision change conditions, etc.

[0039] Specifically, after determining the identity information of the target object, the fundus camera will connect to the patient data management system or the electronic medical record system. The fundus camera uses the obtained identity information as a retrieval keyword to query the relevant database. The fundus camera will not only obtain the most recent examination record but also retrieve all available historical data for comprehensive analysis. The data obtained can include past fundus images, refractive power change records, intraocular pressure measurement results, vision examination data, etc. The fundus camera will perform preliminary processing and collation on these data to prepare for subsequent analysis and use.

[0040] In some embodiments, the acquisition and processing of historical detection data can be achieved in various ways: Optionally, the fundus camera can adopt a distributed database query method. First, the fundus camera looks up relevant records in the local database according to the identity information; if the local data is incomplete, it sends an encrypted query request to the databases of other medical institutions; finally, the fundus camera integrates and deduplicates the data obtained from different sources to form a complete historical detection data set. Optionally, the fundus camera can use intelligent data analysis methods. First, the fundus camera extracts the original historical data from the database; then, it uses machine learning algorithms to clean and standardize the data, removing outliers and redundant information; finally, the fundus camera performs feature extraction and trend analysis on the processed data to generate a summary report containing key information. It can be understood that other methods can also be used to achieve the acquisition and processing of historical detection data, such as using blockchain technology to ensure the security and integrity of data, or using natural language processing technology to extract useful information from unstructured medical records, which are not limited here.

[0041] S103. When it is determined according to the eye image that the eye of the target object is in a preset detection action, an infrared preview image is acquired.

[0042] Among them, the preset detection action refers to a specific state or position in which the eyes of the target object are suitable for fundus examination, including the eyes being opened to an appropriate size, the line of sight being aligned with a specific direction, etc. The infrared preview image refers to an image obtained by irradiating the fundus of the target object with an infrared light source and collecting it. Such an image is usually used for preliminary evaluation and focal length adjustment.

[0043] Specifically, the fundus camera continuously monitors the eye images collected in real time through the fundus camera. When the fundus camera detects that the eye state of the target object meets the preset detection conditions, such as the eyes being fully opened and the pupil position being appropriate, it triggers the infrared light source. The fundus camera then starts to collect a series of infrared preview images. Although this infrared preview image is not as clear as the white light image, it can provide sufficient information for preliminary evaluation of the fundus condition and focal length adjustment, and at the same time causes less irritation to the patient's eyes. The fundus camera continuously collects multiple infrared preview images to ensure obtaining the best-quality images for subsequent analysis.

[0044] In some embodiments, the confirmation of the preset detection action and the acquisition of the infrared preview image can be achieved in various ways: Optionally, the fundus camera can use real-time eye tracking technology. First, the fundus camera captures the eye movement of the target object through a high-speed camera; then, computer vision algorithms are used to analyze the eye position and pupil size in real time; finally, when the eye is detected to be stable and the pupil is of an appropriate size, the infrared light source is automatically triggered and the preview image is captured. Optionally, the fundus camera can adopt a method combining voice guidance and image feedback. First, the fundus camera guides the target object to adjust the eye position through voice commands; then, the eye image is displayed in real time and visual markers are used to indicate the ideal position; finally, when the image analysis algorithm confirms that the eye position is correct, the acquisition of the infrared preview image is automatically started. It can be understood that other methods can also be used to achieve the confirmation of the preset detection action and the acquisition of the infrared preview image, such as using artificial intelligence to assist in judging the best shooting time, or combining virtual reality technology to provide more intuitive visual guidance, which are not limited herein.

[0045] S104. Determine a first focal length of the target object under infrared light irradiation according to the infrared preview image.

[0046] The first focal length represents the distance from the lens to the fundus that can obtain a clear fundus image under infrared light irradiation.

[0047] Specifically, the fundus camera quickly analyzes a series of acquired infrared preview images. First, the fundus camera uses image processing algorithms to evaluate the clarity of each image, including methods such as edge detection and contrast analysis. Then, the fundus camera selects the best infrared preview image according to the clarity score. For the selected image, the fundus camera further analyzes the fundus structure features therein, such as the clarity of the optic disc, blood vessels, etc. Combining these analysis results and the optical parameters of the fundus camera, the fundus camera uses a specific algorithm to calculate the focal length value that can obtain the clearest infrared fundus image, that is, the first focal length.

[0048] In some embodiments, the determination of the first focal length can be achieved in various ways: Optionally, the fundus camera can use an autofocus algorithm. First, the fundus camera quickly acquires multiple infrared preview images at different focal length positions; then, calculate the sharpness score for each image, such as using the Laplacian operator to evaluate the sharpness of the image; finally, find the focal length corresponding to the highest point of the sharpness score through interpolation or curve fitting methods and determine it as the first focal length. Optionally, the fundus camera can adopt a deep learning method. First, train a convolutional neural network model using a large number of labeled fundus images, and this model can evaluate the sharpness of the image and predict the optimal focal length; then, input the acquired infrared preview image into the trained model; finally, the model directly outputs the predicted optimal focal length value as the first focal length. It can be understood that other ways can also be used to achieve the determination of the first focal length, such as optimizing the focal length calculation by combining wavefront aberration analysis technology, or using multispectral imaging technology to improve the accuracy of focal length estimation, which is not limited here.

[0049] S105. Determine the second focal length of the target object under white light illumination according to the first focal length and historical detection data.

[0050] Among them, the second focal length represents the distance from the lens to the fundus where a clear fundus image can be obtained under white light illumination. The historical detection data refers to the past fundus examination records of the target object, including information such as previous focal length settings and refractive power changes.

[0051] Specifically, the fundus camera will first analyze the focal length records in the historical detection data, especially the focal length differences under infrared light and white light illumination. The fundus camera will establish a personalized focal length conversion model, taking into account factors such as the eye characteristics, age, and refractive power changes of the target object. Then, the fundus camera inputs the just-determined first focal length (the focal length under infrared light) into this model. The model will predict the possible optimal focal length under white light illumination based on the historical data and the current first focal length. The fundus camera will also consider the current state of the target object, such as pupil size and intraocular pressure, and fine-tune the prediction result to finally determine the second focal length.

[0052] In some embodiments, the determination of the second focal length can be achieved in various ways: Optionally, the fundus camera can use a statistical regression method. First, extract the corresponding relationship between the infrared focal length and the white light focal length from historical data; then, use a multiple linear regression or non-linear regression model to establish a mapping function from the infrared focal length to the white light focal length; finally, input the current first focal length into this function to calculate the predicted second focal length. Optionally, the fundus camera can adopt a machine learning method. First, train a neural network model using historical data, with inputs including features such as the infrared focal length, patient age, refractive power, etc., and the output being the white light focal length; then, input the current first focal length and relevant information of the target object into the trained model; finally, the predicted value output by the model is the second focal length. It can be understood that other ways can also be used to determine the second focal length, such as dynamically adjusting the focal length prediction using a fuzzy logic control algorithm, or combining optical coherence tomography (OCT) technology to improve the accuracy of focal length conversion, which is not limited here.

[0053] S106. Using the second focal length as the focusing setting information, obtain the fundus image of the target object.

[0054] Among them, the focusing setting information refers to the parameters used to control the position of the fundus camera lens. The fundus image represents a high-resolution digital image that clearly records the fundus structure of the target object under white light illumination.

[0055] Specifically, the fundus camera will first convert the calculated second focal length value into a focusing control parameter that can be recognized by the fundus camera optical system. Then, the fundus camera will precisely control the lens movement mechanism to adjust the lens to the position corresponding to the second focal length. After the adjustment is completed, the fundus camera will activate the white light source to illuminate the fundus of the target object. After ensuring that the light intensity and uniformity meet the requirements, the fundus camera will trigger the image sensor to capture the fundus image. To ensure the image quality, the fundus camera will take one fundus image, or continuously take multiple images, and select the clearest and best-contrasted one as the final fundus image. The whole process will be carried out quickly to reduce the stimulation to the eyes of the target object.

[0056] In some embodiments, the acquisition of fundus images can be achieved in various ways: Optionally, a fundus camera can use multi-exposure synthesis technology. First, the fundus camera takes multiple fundus images with different exposure times in quick succession based on the second focal length; then, these images are synthesized using a high dynamic range (HDR) algorithm; finally, color balance and detail enhancement processing are performed on the synthesized image to obtain the final high-quality fundus image. Optionally, the fundus camera can adopt a real-time image quality assessment and adaptive adjustment method. First, the fundus camera starts shooting at the second focal length while analyzing the image quality in real time; then, if it detects that some areas of the image are unclear, the fundus camera fine-tunes the focal length and lighting parameters; finally, when the preset quality standard is reached, the final image is automatically captured and saved. It can be understood that other methods can also be used to acquire fundus images, such as using light field camera technology to achieve digital refocusing later, or combining artificial intelligence to assist the fundus camera in real-time optimizing shooting parameters, which are not limited here.

[0057] In the above embodiments, the intelligent fundus camera can automatically adapt to the eye characteristics of different patients and optimize the imaging process. In practical applications, this technology can be used not only for routine fundus examinations but also extended to various scenarios such as long-term disease monitoring. Please refer to Figure 2 , which is another schematic flowchart of the imaging method of the fundus camera in the embodiments of this application.

[0058] S201. Collect the eye images of the target object and determine the identity information of the target object based on the eye images.

[0059] Referring to step S101, the fundus camera determines the identity information of the target object.

[0060] S202. Obtain the historical detection data of the target object according to the identity information.

[0061] Referring to step S102, the fundus camera obtains the historical detection data of the target object.

[0062] S203. When it is determined that the eyes of the target object are in a preset detection action according to the eye images, obtain an infrared preview image.

[0063] Referring to step S103, the fundus camera obtains an infrared preview image.

[0064] In some embodiments, the fundus camera obtains the left-eye and right-eye images of the binocular camera module of the fundus camera; calculates the initial distance between the eyes of the target object and the binocular camera module according to the image deviation position of the preset reference object in the left-eye and right-eye images; and determines the initial focal length when the target object performs infrared preview according to the initial distance.

[0065] Among them, the binocular camera module refers to an image acquisition system composed of two camera lenses placed side by side. The left eye image and the right eye image represent the eye images of the target object taken simultaneously by the left and right lenses respectively. The preset reference object refers to a specific marker point or structure used for distance measurement in the image, such as the corner of the eye or the center of the pupil. The image deviation position is used to represent the relative position difference of the same reference object in the left and right images. The initial distance refers to the straight-line distance from the eye of the target object to the binocular camera module. The initial focal length represents the starting focal length value of the infrared preview preset based on the initial distance.

[0066] Specifically, before starting the fundus examination, the fundus camera will first activate the binocular camera module. The binocular camera module will simultaneously capture two eye images, one on the left and one on the right. The fundus camera then analyzes these two images to identify predefined reference objects, such as the corners of the eyes or the edges of the pupils. Then, the fundus camera accurately measures the pixel coordinate differences of these reference objects in the left and right images. Using this difference value and combining with the optical parameters of the binocular camera (such as the baseline distance and the focal length), the fundus camera calculates the accurate distance from the eye of the target object to the camera through the principle of triangulation. Finally, the fundus camera substitutes this distance value into a preset optical formula to calculate a suitable initial focal length value as the starting setting for the infrared preview stage.

[0067] S204. Extract the edge features of the infrared preview image and determine the corresponding clarity evaluation index according to the edge features.

[0068] Among them, the edge feature represents the sharpness of the object contour and details in the image. The clarity evaluation index refers to a numerical standard used to quantify the clarity of the image.

[0069] Specifically, after obtaining the infrared preview image, the fundus camera starts to process it. First, the fundus camera preprocesses the image, such as denoising and contrast enhancement. Then, the fundus camera applies edge detection algorithms, such as the Sobel or Canny operator, to extract the edge information in the image. The fundus camera focuses on the edge features of key structures such as the fundus blood vessels and the edges of the optic disc. Then, the fundus camera calculates the intensity and distribution of these edges to obtain a numerical index reflecting the overall clarity of the image. This index can be the average gradient of the edge pixels, the energy ratio of the high-frequency components, etc.

[0070] In some embodiments, edge feature extraction and sharpness evaluation can be achieved in various ways: Optionally, a fundus camera can use a multi-scale edge analysis method. First, the fundus camera performs a multi-layer pyramid decomposition on the image; then, edge detection operators are applied separately at each scale; finally, the edge information of each scale is integrated, and a weighted average is calculated to obtain the final sharpness index. Optionally, the fundus camera can adopt a sharpness evaluation method based on machine learning. First, a convolutional neural network model is trained using a large number of labeled fundus images; then, the current infrared preview image is input into the model; finally, the model directly outputs a score representing the sharpness of the image. It can be understood that other methods can also be used to achieve edge feature extraction and sharpness evaluation, such as analyzing the frequency domain features of the image by combining wavelet transform, or using phase consistency analysis to evaluate the structural sharpness of the image, which are not limited here.

[0071] S205. When the sharpness evaluation index reaches the preset sharpness threshold, record the corresponding target focal length position.

[0072] Among them, the preset sharpness threshold refers to the lowest acceptable value of the sharpness evaluation index predefined by the fundus camera. The target focal length position represents the distance setting of the current lens relative to the fundus.

[0073] Specifically, the fundus camera continuously monitors the sharpness evaluation index calculated in the previous step. When it detects that the index value first reaches or exceeds the preset sharpness threshold, the fundus camera triggers a recording operation. This preset threshold is usually determined based on a large amount of experimental data and expert experience. The fundus camera accurately records the position parameters of the lens at this time, which can include the step value of the focus motor, the zoom ratio of the optical fundus camera, etc. These data will be temporarily stored in the high-speed cache of the fundus camera for subsequent quick access and processing.

[0074] In some embodiments, clear threshold judgment and target focal length position recording can be achieved in various ways: Optionally, the fundus camera can use a dynamic threshold adjustment method. First, the fundus camera starts the evaluation according to the initial preset threshold; then, as the evaluation process progresses, the fundus camera dynamically adjusts the threshold according to the change trend of the image quality; finally, when the sharpness index stably exceeds the adjusted threshold, record the corresponding focal length position. Optionally, the fundus camera can adopt a multi-point sampling comparison method. First, the fundus camera quickly acquires images at multiple different focal length positions within a certain range; then, calculate the sharpness evaluation index for each position; finally, select the position with the highest sharpness and exceeding the preset threshold as the target focal length position and record it. It can be understood that other methods can also be used to achieve clear threshold judgment and target focal length position recording, such as using a fuzzy logic control algorithm to optimize the threshold judgment process, or combining eye movement tracking technology to adjust the focal length recording strategy in real time, which are not limited here.

[0075] S206. Calculate the first focal length based on the optical system parameters of the fundus camera and the target focal length position.

[0076] Among them, the optical system parameters refer to a series of values describing the optical performance of the fundus camera, including lens focal length, aperture size, sensor size, etc. The first focal length represents the ideal distance from the lens to the fundus at which a clear fundus image can be obtained under infrared light irradiation.

[0077] Specifically, after the fundus camera records the target focal length position, it will start the focal length calculation process. First, the fundus camera will call the pre-stored optical system parameters of the fundus camera, which are usually determined during camera calibration. Then, the fundus camera combines the data of the target focal length position with these optical parameters and substitutes them into a specific optical calculation formula. This formula takes into account factors such as the magnification of the lens and the optical path length. Through complex calculations, the fundus camera converts the mechanical position parameters into the actual physical focal length value, that is, the first focal length, which represents the ideal distance from the lens to the fundus when a clear fundus image is obtained under infrared light.

[0078] S207. Determine the second focal length of the target object under white light irradiation based on the first focal length and historical detection data.

[0079] Referring to step S105, the fundus camera will determine the second focal length of the target object.

[0080] In some embodiments, the fundus camera extracts multiple detection records of the target object from the historical detection data; the detection records include the infrared focal length of the target object under infrared light, the white light focal length under white light, and the historical diopter at the time of detection; calculate the focusing deviation value between the infrared focal length and the white light focal length; establish a deviation prediction model based on the focusing deviation value and the corresponding historical diopter; input the first focal length and the current diopter of the target object into the deviation prediction model to obtain a predicted deviation value; calculate the second focal length based on the first focal length and the predicted deviation value.

[0081] Among them, the infrared focal length and the white light focal length respectively refer to the lens focal length values when clear images are obtained under different light sources. The diopter is used to represent the measure of the refractive power of the eye. The focusing deviation value refers to the difference between the infrared focal length and the white light focal length.

[0082] Specifically, after determining the first focal length, the fundus camera will access the database to retrieve the historical detection data of the target object. The fundus camera will filter out multiple records containing complete focal length and diopter information, usually selecting several recent examination results. Then, the fundus camera will calculate the difference between the infrared focal length and the white light focal length in each record to obtain a series of historical focusing deviation values. Next, the fundus camera uses these deviation values and the corresponding historical diopter data to construct a deviation prediction model through regression analysis or machine learning algorithms. After the model is established, the fundus camera will input the currently obtained first focal length (i.e., the infrared focal length) and the latest diopter data of the target object, and the model will output a predicted deviation value. Finally, the fundus camera adds the first focal length to this predicted deviation value to obtain the predicted white light focal length, which is the second focal length.

[0083] In some embodiments, the deviation prediction and the calculation of the second focal length can be achieved in various ways: Optionally, the fundus camera can use the multiple linear regression method. First, the fundus camera takes the diopter and the infrared focal length in the historical data as independent variables and the focusing deviation value as the dependent variable; then, it uses the least squares method to fit a linear regression equation; finally, it substitutes the current first focal length and diopter into the equation to calculate the predicted deviation value, and thus determines the second focal length. Optionally, the fundus camera can adopt the support vector regression (SVR) algorithm. First, the fundus camera performs feature engineering on the historical data to extract relevant features; then, it uses methods such as grid search to optimize the hyperparameters of the SVR and trains the deviation prediction model; finally, it inputs the current data into the trained SVR model to obtain the predicted deviation value and calculates the second focal length. It can be understood that other ways can also be used to achieve the deviation prediction and the calculation of the second focal length, such as using a neural network to construct a non-linear prediction model, or combining the Bayesian optimization method to dynamically adjust the prediction strategy, which is not limited here.

[0084] S208. Using the second focal length as the focusing setting information, obtain the fundus image of the target object.

[0085] Referring to step S106, the fundus camera will obtain the fundus image of the target object.

[0086] In some embodiments, the fundus camera will perform feature analysis on the fundus structure in the fundus image to obtain the lesion detection result; combine the historical detection data to determine the pathological evolution indication of the lesion detection result; and generate a detection report according to the pathological evolution indication.

[0087] Among them, the fundus structure refers to various anatomical features on the retina, such as the optic disc, macula, blood vessels, etc. Feature analysis means quantitatively or qualitatively evaluating the morphology, color, distribution, etc. of these structures. The lesion detection result refers to the area or phenomenon with pathological changes found through analysis. The pathological evolution indication is used to represent the trend of the lesion state changing over time.

[0088] Specifically, after the fundus camera obtains high-quality fundus images, it will initiate an automatic analysis process. First, the fundus camera uses an image segmentation algorithm to identify and locate the main fundus structures. Then, the fundus camera performs detailed feature extraction on each structure, such as measuring the size of the optic disc, analyzing the blood vessel orientation, and evaluating the integrity of the macula region. The fundus camera compares these features with normal reference values to identify possible abnormal regions. Next, the fundus camera accesses historical detection data, compares the current lesion detection results with past records, and analyzes the development trend of the lesions. Based on this longitudinal comparison, the fundus camera generates a pathological evolution indication to describe the stability, progression, or improvement of the lesions. Finally, the fundus camera integrates information such as the current detection results, historical comparison analysis, and pathological evolution prediction, and automatically generates a structured detection report.

[0089] In some embodiments, fundus lesion detection and report generation can be achieved in various ways: Optionally, the fundus camera can use a deep learning-based lesion detection method. First, the fundus camera uses a pre-trained convolutional neural network to extract features from the fundus image; then, a target detection algorithm is used to locate potential lesion regions; finally, a classification model is used to determine the specific lesion type for each detected region and generate detailed detection results. Optionally, the fundus camera can adopt a rule-based expert fundus camera method. First, the fundus camera constructs a detailed diagnostic rule library based on the professional knowledge text file of ophthalmologists; then, the extracted fundus features are input into this rule fundus camera for reasoning; finally, the fundus camera gives a lesion diagnosis opinion based on the reasoning result and generates a personalized detection report based on a preset report template. It can be understood that other methods can also be used to achieve fundus lesion detection and report generation, such as combining multi-modal image fusion technology to improve diagnostic accuracy, or using natural language processing technology to generate more understandable report descriptions, which are not limited here.

[0090] S209. Identify overexposed regions and underexposed regions in the fundus image.

[0091] Among them, the overexposed region refers to the part of the image with too high brightness and lost details. The underexposed region refers to the image region with too low brightness and unclear details.

[0092] Specifically, after obtaining the fundus image, the fundus camera will start the analysis process. First, the fundus camera will convert the color fundus image into a grayscale image for brightness analysis. Then, the fundus camera will calculate the brightness histogram of the entire image to understand the overall distribution of pixel brightness. Based on this distribution, the fundus camera will set the thresholds for high brightness and low brightness. Next, the fundus camera will scan the entire image pixel by pixel, marking the areas where the brightness exceeds the high threshold as overexposed and the areas where the brightness is below the low threshold as underexposed. The fundus camera can also consider local contrast to more accurately identify problem areas.

[0093] In some embodiments, the fundus camera will determine the HSV color space corresponding to the fundus image; calculate the distribution histogram of the pixel values in the V channel of the HSV color space; determine the high brightness threshold and the low brightness threshold according to the distribution histogram; identify the areas where the V channel pixel values are higher than the high brightness threshold as overexposed areas; and identify the areas where the V channel pixel values are lower than the low brightness threshold as underexposed areas.

[0094] Among them, the HSV color space refers to a three-dimensional color model with hue, saturation, and value as coordinates. The V channel represents the component representing brightness in the HSV model. The distribution histogram refers to a statistical chart describing the distribution of pixel values at different brightness levels. The high brightness threshold and the low brightness threshold respectively represent the critical values for judging overexposure and underexposure. The overexposed area refers to the part of the image with abnormally high brightness, and the underexposed area refers to the part with abnormally low brightness.

[0095] Specifically, after obtaining the fundus image, the fundus camera will first convert the image from the RGB color space to the HSV color space. This conversion helps to better separate the brightness information. Then, the fundus camera will focus on the V channel of the HSV space and calculate the value distribution of all pixels on the V channel. The fundus camera will generate a histogram showing the number of pixels at different brightness levels. Based on this histogram, the fundus camera will use statistical methods such as percentiles or standard deviations to determine the high brightness and low brightness thresholds. After determining the thresholds, the fundus camera will scan the V channel of the entire image pixel by pixel. For pixels with V values exceeding the high brightness threshold, the fundus camera will mark them as overexposed; for pixels with V values below the low brightness threshold, the fundus camera will mark them as underexposed. Finally, the fundus camera will generate a mask map of the exposure problem area for subsequent image optimization processing.

[0096] In some embodiments, the identification of the exposure abnormal area can be achieved in various ways: Optionally, the fundus camera can use the adaptive threshold method. First, the fundus camera calculates the global mean and standard deviation of the V channel; then, the mean plus or minus several standard deviations is used as the initial high and low thresholds; finally, the fundus camera dynamically adjusts these thresholds within the local area to adapt to the brightness characteristics of different areas, so as to more accurately identify the exposure abnormal area. Optionally, the fundus camera can adopt a clustering-based method. First, the fundus camera performs K-means clustering on the pixel values of the V channel, usually selecting 3 to 5 categories; then, it analyzes the central values of each category, and regards the highest and lowest categories as potential overexposed and underexposed areas respectively; finally, the fundus camera combines the spatial continuity information to determine the boundaries of these areas and obtain the final exposure abnormal area. It can be understood that other methods can also be used to identify the exposure abnormal area, such as using the local contrast analysis method to improve the robustness of the identification, or combining a deep learning model to directly learn the characteristics of exposure abnormality from the image, which is not limited here.

[0097] S210. Use the tone mapping algorithm to process the overexposed area and the underexposed area respectively to obtain the tone-optimized area.

[0098] Among them, the tone mapping algorithm refers to a mathematical method used to adjust the brightness and contrast of an image, aiming to expand the dynamic range and enhance details. The tone-optimized area refers to the image area whose visual effect is improved after being adjusted by the algorithm.

[0099] Specifically, after the fundus camera identifies the exposure abnormal area, it will adopt corresponding tone mapping strategies for different types of areas. For the overexposed area, the fundus camera will use an algorithm to compress the highlights, reduce the brightness and try to restore the lost details. For the underexposed area, the fundus camera will apply an algorithm to enhance the shadows, increase the brightness and enhance the contrast. These algorithms usually consider the human eye perception characteristics to ensure that the processed image looks natural and harmonious. The fundus camera will use a local adaptive method to dynamically adjust the mapping parameters according to the characteristics of the surrounding areas to achieve the best optimization effect.

[0100] In some embodiments, tone mapping and optimization can be achieved in various ways: Optionally, the fundus camera can use a multi-scale fusion method. First, the fundus camera performs multi-scale decomposition on the original image; then, tone mapping algorithms are applied separately at different scales; finally, the processed results at each scale are weighted and fused to obtain the final tone-optimized region. Optionally, the fundus camera can adopt a tone optimization method based on deep learning. First, a generative adversarial network (GAN) is trained using a large number of high-quality fundus images; then, the identified exposure-abnormal regions are input into the trained GAN; finally, the GAN generates an optimized region image with better visual effects. It can be understood that other ways can also be adopted to achieve tone mapping and optimization, such as using an adaptive tone mapping algorithm based on retinal anatomical structure, or combining the human eye visual perception model to optimize the processing effect, which is not limited here.

[0101] S211. Restore the tone-optimized region to the fundus image to obtain the fundus-optimized image.

[0102] Among them, the fundus-optimized image represents the final high-quality fundus image after tone adjustment and detail enhancement.

[0103] Specifically, after the fundus camera completes the tone optimization of the local region, it will start the image fusion process. First, the fundus camera creates a blank layer with the same size as the original fundus image. Then, the fundus camera accurately locates the optimized region to the corresponding position on this layer. To avoid obvious boundaries between the processed region and the unprocessed region, the fundus camera applies a gradient blending algorithm in the edge region, including using feathering or alpha-channel blending techniques. The fundus camera also performs global color balance adjustment to ensure the overall tone of the image is coordinated. Finally, the fundus camera merges the fused layer with the original image to generate the final fundus-optimized image.

[0104] In some embodiments, the restoration of the tone optimization region and the generation of the final image can be achieved in various ways: Optionally, the fundus camera can use Poisson image editing technology. First, the fundus camera calculates the gradient fields of the optimization region and the original image; then, the Poisson equation is used to solve for the best fusion result; finally, the solution result is combined with the original image to obtain a seamlessly fused optimized fundus image. Optionally, the fundus camera can adopt a multi-resolution spline interpolation method. First, the fundus camera performs multi-scale decomposition on the original image and the optimization region; then, the spline interpolation algorithm is used for fusion at each scale; finally, the fusion results at each scale are reconstructed to obtain the final optimized fundus image. It can be understood that other methods can also be used to achieve the restoration of the tone optimization region and the generation of the final image, such as using deep learning-based image restoration technology to achieve a more natural fusion effect, or combining retinal vascular structure information to guide the fusion process to maintain the continuity of the anatomical structure, which is not limited here.

[0105] In the embodiments of the present application, due to the adoption of an intelligent adaptive focusing fundus camera based on historical data and infrared preview, combined with real-time image processing and lesion analysis technologies, high-quality fundus images can be quickly and accurately obtained, and in-depth pathological analysis can be provided, effectively solving the problems of complex operation, time-consuming examination, unstable image quality, and low analysis efficiency of traditional fundus cameras. Furthermore, high-efficiency and high-quality fundus examination and diagnosis are achieved. It not only improves the work efficiency of ophthalmologists and reduces the discomfort of patients, but also provides effective support for the early detection and long-term monitoring of fundus diseases.

[0106] The following describes the fundus camera in the embodiments of the present invention application from the perspective of hardware processing. Please refer to Figure 3 , which is a schematic structural diagram of an entity device of the fundus camera in the embodiments of the present application.

[0107] It should be noted that Figure 3 the structure of the fundus camera shown is only an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present invention.

[0108] Such as Figure 3As shown, the fundus camera includes a Central Processing Unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the Read-Only Memory (ROM) 302 or the program loaded from the storage section 308 into the Random Access Memory (RAM) 303, such as executing the method described in the above embodiments. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other 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 the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a Liquid Crystal Display (LCD), an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read from it can be installed into the storage section 308 as needed.

[0110] Specifically, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by the Central Processing Unit (CPU) 301, various functions defined in the present invention are executed.

[0111] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections with 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 fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium that contains or stores a program, and this program 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 possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings.

[0113] Specifically, the fundus camera of this embodiment includes a processor and a memory. A computer program is stored on the memory. When the computer program is executed by the processor, the imaging method of the fundus camera provided in the above embodiment is implemented.

[0114] On the other hand, the present invention also provides a computer-readable storage medium. This storage medium can be included in the fundus camera described in the above embodiment; or it can exist separately and not be assembled into the fundus camera. The above storage medium carries one or more computer programs. When the above one or more computer programs are executed by a processor of a fundus camera, the fundus camera implements the imaging method of the fundus camera provided in the above embodiment.

[0115] As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application.

[0116] As used in the foregoing embodiments, depending on the context, the term "when" may be construed to mean "if", or "after", or "in response to determining", or "in response to detecting". Similarly, depending on the context, the phrase "upon determining" or "if (the stated condition or event) is detected" may be construed to mean "if determined", or "in response to determining", or "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0117] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by a computer program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the foregoing method embodiments. The foregoing storage medium includes various media that can store program codes, such as ROM or random access memory RAM, magnetic disks, or optical discs.

Claims

1. An imaging method for a fundus camera, characterized in that, Applied to a fundus camera, the method includes: Collect an eye image of a target object, and determine the identity information of the target object according to the eye image; Obtain the historical detection data of the target object according to the identity information; When it is determined according to the eye image that the eyes of the target object are in a preset detection action, obtain an infrared preview image; Determine a first focal length of the target object under infrared light irradiation according to the infrared preview image; Determine a second focal length of the target object under white light irradiation according to the first focal length and the historical detection data; The determining the second focal length of the target object under white light irradiation according to the first focal length and the historical detection data specifically includes: extracting multiple detection records of the target object from the historical detection data; the detection records include the infrared focal length of the target object under infrared light, the white light focal length under white light, and the historical diopter at the time of detection; calculating the focusing deviation value between the infrared focal length and the white light focal length; establishing a deviation prediction model according to the focusing deviation value and the corresponding historical diopter; inputting the first focal length and the current diopter of the target object into the deviation prediction model to obtain a predicted deviation value; calculating and obtaining the second focal length according to the first focal length and the predicted deviation value; Using the second focal length as the focusing setting information, obtain a fundus image of the target object.

2. The method according to claim 1, wherein There are multiple infrared preview images, and each infrared preview image corresponds to a focal length position; The determining the first focal length of the target object under infrared light irradiation according to the infrared preview image specifically includes: Extract the edge features of the infrared preview image, and determine the corresponding clarity evaluation index according to the edge features; When the clarity evaluation index reaches a preset clarity threshold, record the corresponding target focal length position; Calculate and obtain the first focal length according to the optical system parameters of the fundus camera and the target focal length position.

3. The method according to claim 1, wherein After the step of obtaining the fundus image of the target object using the second focal length as the focusing setting information, the method further includes: Identify overexposed areas and underexposed areas in the fundus image; Use a tone mapping algorithm to process the overexposed area and the underexposed area respectively to obtain a tone-optimized area; Restore the tone-optimized area to the fundus image to obtain an optimized fundus image.

4. The method according to claim 3, wherein The identifying the overexposed areas and the underexposed areas in the fundus image specifically includes: Determine the HSV color space corresponding to the fundus image; Calculate the distribution histogram of the V-channel pixel values in the HSV color space; Determine a high brightness threshold and a low brightness threshold according to the distribution histogram; Identify the area where the V-channel pixel value is higher than the high brightness threshold as the overexposed area; Identify the area where the V-channel pixel value is lower than the low brightness threshold as the underexposed area.

5. The method according to claim 1, wherein Before the step of obtaining the infrared preview image when it is determined according to the eye image that the eyes of the target object are in a preset detection action, the method further includes: Obtain the left-eye image and right-eye image of the eye captured by the binocular camera module of the fundus camera; Calculate the initial distance between the eye of the target object and the binocular camera module according to the image deviation position of the preset reference object in the left-eye image and the right-eye image; Determine the initial focal length when the target object performs infrared preview according to the initial distance; 6. The method according to claim 1, wherein After the step of obtaining the fundus image of the target object with the second focal length as the focusing setting information, the method further includes: Perform feature analysis on the fundus structure in the fundus image to obtain a lesion detection result; Combine the historical detection data to determine the pathological evolution indication of the lesion detection result; Generate a detection report according to the pathological evolution indication; 7. An fundus camera, characterized in that, The 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 includes computer instructions, and the one or more processors call the computer instructions to enable the fundus camera to execute the method according to any one of claims 1-6; 8. A computer-readable storage medium, comprising instructions, characterized in that, When the instruction runs on the fundus camera, the fundus camera is enabled to execute the method according to any one of claims 1-6; 9. A computer program product, characterized in that, When the computer program product runs on the fundus camera, the fundus camera is enabled to execute the method according to any one of claims 1-6;

Images