Imaging display method and system of slit-lamp microscope, medium and product

Abstract

The invention discloses an imaging display method and system of a slit-lamp microscope, a medium and a product, and relates to the field of ophthalmology detection, and the method comprises the steps: obtaining a first eye video of a target object through employing a first resolution after an acquisition starting instruction of a user is received; determining an eye movement track of the target object according to the first eye video; obtaining a second eye video by using a second resolution after determining that the eyes of the target object meet the collection condition according to the eye movement track; the second resolution is higher than the first resolution; intercepting a target video frame meeting the detection requirement in the second eye video to obtain a target image; and marking the target image to obtain a detection image, and displaying the detection image. By implementing the method, image capture under the eye movement condition can be optimized, and storage resources are saved.

Description

Technical Field

[0001] The present application relates to the field of ophthalmic testing, and in particular to an imaging display method, system, medium and product of a slit lamp microscope. Background Art

[0002] With the continuous advancement of medical technology, the requirements for image quality and information volume in ophthalmic diagnosis are increasing. As a basic device for ophthalmic examination, slit lamp microscope plays a key role in the observation and diagnosis of anterior segment structures such as the cornea, lens and anterior chamber. High-quality, multi-dimensional eye images not only help doctors diagnose eye diseases more accurately, but also provide patients with a more intuitive explanation of their condition, thereby improving diagnosis and treatment results and patient satisfaction.

[0003] The related slit lamp microscope imaging method uses a preset optical system for image acquisition, and mainly relies on doctors to observe different levels of eye structures by adjusting the slit width, angle and magnification. The digital camera module in the optical system can capture a series of two-dimensional slice images for users to perform basic image optimization operations such as brightness adjustment and contrast enhancement.

[0004] However, when the related technology is used for eye imaging detection using a slit lamp microscope, factors such as the patient's eye movements or tear film changes can cause image blur, resulting in longer detection time. At this time, the long-term acquisition of high-definition images will occupy more storage resources. Summary of the invention

[0005] The present application provides an imaging display method, system, medium and product of a slit lamp microscope, which are used to optimize image capture under eye movement conditions and save storage resources.

[0006] In a first aspect, the present application provides an imaging display method for a slit lamp microscope, which is applied to a display system, and the method includes: after receiving a user's acquisition start instruction, using a first resolution to acquire a first eye video of a target object; determining the eye movement trajectory of the target object based on the first eye video; after determining that the eye of the target object meets the acquisition conditions based on the eye movement trajectory, using a second resolution to acquire a second eye video; the second resolution is higher than the first resolution; intercepting a target video frame that meets the detection requirements in the second eye video to obtain a target image; marking the target image to obtain a detection image and displaying the detection image.

[0007] In the above embodiment, the display system first uses low resolution to obtain the initial eye video and analyzes the eye movement of the target object; when it is determined that the eye meets the acquisition conditions, high resolution is used to obtain a clearer eye video. This hierarchical acquisition method can not only ensure image quality, but also effectively save storage resources; by intercepting video frames that meet the detection requirements and marking them, higher quality detection images are obtained, thereby improving the efficiency and accuracy of ophthalmic examinations.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the eye movement trajectory includes an eyelid movement trajectory and an eyeball movement trajectory; after determining that the target object's eyes meet the acquisition conditions according to the eye movement trajectory, using the second resolution to obtain a second eye video, specifically including: calculating the eyelid stability index of the eyelid movement trajectory and the eyeball stability index of the eyeball movement trajectory; when the eyelid stability index is higher than a first preset threshold and the eyeball stability index is higher than a second preset threshold, determining the position information of the target object's eyes according to the first eye video; after adjusting the shooting focal length and shooting angle of the shooting module according to the position information, using the second resolution to obtain the second eye video.

[0009] In the above embodiment, the display system ensures high-resolution image acquisition when the target object's eyes are in a relatively stable state by calculating the stability index of the eyelids and eyeballs; it also adjusts the focal length and angle of the shooting module according to the eye position information, thereby further improving the clarity and accuracy of the image.

[0010] In combination with some embodiments of the first aspect, in some embodiments, target video frames that meet the detection requirements in the second eye video are intercepted to obtain a target image, specifically including: intercepting multiple frame images of the second eye video according to a preset frame interval, and calculating the target area integrity score of the frame image; screening out frame images whose target area integrity score is not less than a preset integrity threshold to obtain candidate frames; performing feature point matching on the candidate frames, and selecting N target video frames with the highest feature point matching degrees; and performing image fusion on the N target video frames to obtain the target image.

[0011] In the above embodiment, the display system screens candidate frames according to the target area integrity score when capturing the target video frame, and also performs image fusion processing, thereby ensuring that the final target image is complete and clear, thereby improving the accuracy and diagnostic efficiency of ophthalmic examinations.

[0012] In combination with some embodiments of the first aspect, in some embodiments, before the step of intercepting multiple frame images of the second eye video according to a preset frame interval and calculating the target area integrity score of the frame image, the method also includes: intercepting the image of each frame of the second eye video to obtain a set of original frame images; determining the original frame images in the original frame image set whose clarity is lower than a preset clarity threshold as the frame images to be optimized, and determining the pixel blocks to be optimized of the frame images to be optimized; obtaining a preset number of preceding frame images and following frame images of the frame images to be optimized; completing the pixel blocks to be optimized of the frame images to be optimized based on the preceding frame images and the following frame images to obtain the optimized frame image; replacing the frame images to be optimized in the original frame image set with the optimized frame images to obtain the optimized second eye video.

[0013] In the above embodiment, for frames with insufficient clarity, the display system completes the pixel blocks to be optimized by analyzing the information of the previous and next frames, thereby improving the overall video quality, improving the image clarity, ensuring the video continuity, and facilitating image analysis and accurate diagnosis.

[0014] In combination with some embodiments of the first aspect, in some embodiments, before the step of obtaining a first eye video of the target object using a first resolution, the method also includes: obtaining an eye image of the target object, and determining the identity information of the target object based on the eye image; obtaining a historical inspection record of the target object based on the identity information; based on the historical inspection record, generating a key focus area for this inspection, and displaying the key focus area.

[0015] In the above embodiment, the display system obtains the historical inspection records of the target object and generates the key focus areas for this inspection, which improves the pertinence and efficiency of the inspection, provides more reference information for the user (doctor), and helps to discover subtle changes and long-term development trends of eye lesions.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the steps of marking the target image, obtaining a detection image and displaying the detection image, the method also includes: storing the detection image in a historical inspection record; obtaining pathological diagnosis information input by a user; generating a pathological development report of the target object based on the historical inspection record, the detection image and the pathological diagnosis information, and displaying the pathological development report.

[0017] In the above embodiment, after completing the detection, the display system generates a pathology development report based on the diagnostic information input by the user (doctor), which facilitates the long-term tracking of the patient's condition, provides the user with a more comprehensive basis for condition analysis, and is conducive to formulating a more accurate treatment plan.

[0018] In combination with some embodiments of the first aspect, in some embodiments, the display system includes a HUD display module; before the step of acquiring a first eye video of the target object using a first resolution, the method also includes: after detecting the user's microscope adjustment operation, acquiring current microscope parameter information including magnification, focal length and lighting intensity; acquiring detection process information and pathology reference information of the target object; and using the HUD display module to display the microscope parameter information, detection process information and pathology reference information in the display light path of the microscope.

[0019] In the above embodiment, the display system uses the HUD display module to display microscope parameter information, detection process information and pathology reference information in real time in the display light path of the microscope, so that the user (doctor) can obtain key information without shifting his or her sight during the examination, thereby improving the efficiency and accuracy of the examination and reducing the doctor's operating burden.

[0020] In a second aspect, an embodiment of the present application provides a display system, comprising: 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 display system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, and when the above-mentioned computer program product runs on a display system, the above-mentioned display system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions. When the instructions are executed on a display system, the display system executes the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] It can be understood that the display system 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 embodiment 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 repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the use of a hierarchical acquisition and screening image acquisition method, by intelligently screening high-resolution videos and capturing target video frames that meet the detection requirements, it is possible to effectively save storage resources while ensuring image quality. The screened target images are also marked to obtain high-quality detection images, which effectively solves the problem of high-resolution images taking up a large amount of storage space for a long time in the prior art, and at the same time improves the efficiency and accuracy of ophthalmic examinations.

[0025] 2. Due to the use of an optimization processing method based on multiple frame images, frames with clarity lower than a preset threshold are identified as frames to be optimized, and the information of adjacent frames is used to complete the low-quality pixel blocks in the frames to be optimized. Therefore, the video quality can be effectively improved and the image continuity can be ensured. The problem of image blur caused by slight eye movements or tear film changes in the prior art is effectively solved, thereby achieving clearer and more coherent eye examination videos, improving the accuracy of image analysis and diagnosis, and providing users with a more reliable diagnostic basis.

[0026] 3. Due to the use of a dynamically updated medical record management system and an intelligent method for generating pathology development reports, combined with the latest diagnostic information input by the doctor to generate pathology development reports, long-term tracking and analysis of the patient's condition can be achieved, effectively solving the problems of fragmented medical record information and isolated diagnostic information in existing technologies, thereby achieving more accurate and personalized ophthalmic diagnosis and treatment plans, and at the same time helping to improve the testing experience of the examinee. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flow chart of the imaging display method of the slit lamp microscope in the embodiment of the present application; Figure 2 is another flow chart of the imaging display method of the slit lamp microscope in the embodiment of the present application; Figure 3 It is a schematic diagram of a physical device structure of a display system in an embodiment of the present application. DETAILED DESCRIPTION

[0028] 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 be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below.

[0031] In a hospital, Doctor A performed a routine examination on an elderly patient with early glaucoma. When using a traditional slit lamp microscope, Doctor A found that the patient's eye movements were more obvious, resulting in frequent blurring during image acquisition. In order to obtain clear images, Doctor A had to repeat the acquisition process many times, which not only prolonged the examination time but also increased the patient's discomfort. At the same time, high-resolution continuous video acquisition generated a large amount of data, which took up a lot of storage space.

[0032] In the related art, a method of continuous image video acquisition can be used to obtain a clear image in the case of slight eye movement. The following describes a scenario of an imaging display method using a slit lamp microscope in the related art.

[0033] Doctor B used a slit lamp microscope system to examine a patient with retinal disease. The system uses high-speed camera technology to capture a large number of high-resolution images. However, during the examination, Doctor B found that although the system can acquire a large number of images, it still cannot effectively deal with the patient's involuntary eye movements, and many captured images are still blurred or out of focus. The massive amount of image data generated during this period takes up a lot of storage space, and the invalid data needs to be manually screened, which is time-consuming and labor-intensive. Simply relying on increasing the acquisition frequency and resolution has brought new data management challenges.

[0034] The imaging display method of the slit lamp microscope in the embodiment of the present application can not only optimize the image blur problem caused by micro-movement of the eyeball through real-time eye movement analysis and resolution adjustment, but also reduce the data storage requirements. The following describes the scenario using the imaging display method of the slit lamp microscope in the present application.

[0035] Doctor C used a new intelligent slit lamp microscope system that adopted the imaging display method of the present application. When examining a patient with diabetic retinopathy, the system first used a low-resolution mode to quickly capture eye movements and analyze the stability of the eyeball and eyelids in real time. When it was detected that the eye was in a relatively stable state, the system automatically switched to high-resolution mode to accurately capture the image of the target area. Throughout the process, the patient's perceived examination time was significantly shortened. Since the system only collects high-resolution images when necessary, data storage requirements are reduced.

[0036] It can be seen that the imaging and display method of the slit lamp microscope in the embodiment of the present application can not only achieve high-quality eye image acquisition, but also effectively solve the problems of waste of storage resources and unstable image quality in traditional methods.

[0037] For ease of understanding, the following describes the process of the method provided by this implementation in combination with the above scenario. Figure 1 , is a flow chart of the imaging display method of the slit lamp microscope in the embodiment of the present application.

[0038] S101. After receiving a capture start instruction from a user, obtain a first eye video of a target object using a first resolution.

[0039] The user is a doctor or technician operating a slit lamp microscope. The acquisition start instruction refers to a signal sent by the user through the input device of the display system to start the eye examination, which can be triggered by clicking a designated icon control. The first resolution represents a relatively low image resolution for quick preview and preliminary analysis. The target object refers to a patient or related person undergoing an eye examination.

[0040] Specifically, the display system is connected to a camera module, which includes an eye camera module and a microscopic camera module, which are respectively arranged on the slit lamp and the microscope optical path (the specific setting position and method are not limited), and are used for macroscopic eye photography and microscopic eye photography. When the doctor issues a collection start instruction through a touch screen, a button, or a voice command, the display system will switch the camera module to an eye camera module using a predefined first resolution (for example, 640x480 pixels), and collect the overall features of the eye image at the macro level. The eye camera module can continuously capture the eye image of the target object to form a first eye video with a duration of a preset time (for example, 5-10 seconds). During this process, the display system will display the collected video images on the display screen in real time for the user to make a preliminary observation.

[0041] S102: Determine an eye movement trajectory of the target object according to the first eye video.

[0042] The eye movement trajectory represents the movement path of the eyeball and eyelid of the target object within a period of time. The first eye video refers to the low-resolution eye image sequence obtained in the previous step.

[0043] Specifically, the display system first preprocesses the first eye video, including denoising and contrast enhancement. Then, the display system uses computer vision algorithms, such as feature point tracking or optical flow, to analyze the position changes of eye feature points (such as iris center, eye corner, etc.) in each frame of the video. Through the differences in the positions of these feature points between consecutive frames, the display system can calculate the movement speed and direction of the eyeball and eyelid, thereby drawing a complete eye movement trajectory.

[0044] In some embodiments, the eye movement trajectory can be determined in a variety of ways: Optionally, the display system can first use the Hough transform algorithm to detect the iris outline in the video; then, mark the position of the iris center in each frame of the image; then, calculate the change in the iris center position between adjacent frames; finally, connect these changes in series to form the eye movement trajectory. Optionally, the display system can first use a cascade classifier to detect the eye area in each frame of the image; then, apply a corner detection algorithm in the eye area to find points with obvious features; then, use the KLT algorithm to track the movement of these feature points between consecutive frames; finally, derive the overall eye movement trajectory based on the collective movement trend of the feature points. It is understandable that other methods can also be used to determine the eye movement trajectory, such as using a deep learning model to directly extract eye movement features from a video sequence, which is not limited here.

[0045] S103: After determining, according to the eye movement trajectory, that the eyes of the target object meet the acquisition condition, obtain a second eye video using a second resolution.

[0046] The second resolution refers to an image resolution higher than the first resolution, which is used to obtain clearer and more detailed eye images.

[0047] Specifically, the display system first analyzes the eye movement trajectory obtained in the previous step, and calculates the movement amplitude and frequency of the eyeball and eyelid. If these parameters are lower than the preset threshold (for example, the eyeball movement amplitude is less than 0.5mm, and the eyelid blinks less than 20 times per minute), the system considers that the target object's eyes meet the acquisition conditions. Subsequently, the display system will switch the camera module to a microscopic camera module, and shoot in a preset second resolution mode (for example, 1920x1080 pixels). The display system will adjust the parameters of the microscopic camera module, including focal length, aperture, and exposure time. The system will then begin to capture a new high-resolution eye video under a microscope, i.e., the second eye video, which lasts for 15-30 seconds to ensure that sufficient image data is obtained.

[0048] In some embodiments, the acquisition of high-resolution eye video can be achieved in a variety of ways: Optionally, the display system can first calculate the best shooting time based on the eye movement trajectory; then, when the best time comes, the system quickly switches to high-resolution mode; then, the system starts the autofocus function to ensure that the eye image is clear; finally, the system continuously captures high-resolution images of a preset length and stores them in real time as a second eye video. Optionally, the display system can first notify the doctor that the eye is stable and ready for high-resolution acquisition; then, the system waits for the doctor's confirmation signal; then, the system switches to high-resolution mode and starts the image stabilization function at the same time; then, the system starts high-speed (high frame rate video) continuous shooting; finally, the system performs real-time motion compensation processing on the captured image sequence to generate a stable second eye video. It is understandable that other methods can also be used to achieve the acquisition of high-resolution eye video, such as using multiple high-resolution cameras to capture images from different angles at the same time, which is not limited here.

[0049] S104, intercepting a target video frame that meets the detection requirements in the second eye video to obtain a target image.

[0050] The target video frame refers to a single image frame selected from the second eye video that best meets the diagnostic requirements. The detection requirements refer to the image quality and content standards required for a specific eye examination. The target image refers to the high-quality eye image that is ultimately used for diagnosis after screening and processing.

[0051] Specifically, the display system performs this step after acquiring the second eye video to extract the most valuable diagnostic image. The display system first sets the screening criteria according to the preset detection requirements (such as clarity, contrast, visibility of specific eye structures, etc.). Then, the system performs a quality assessment on each frame of the second eye video, including image clarity analysis, integrity check of the target area (such as the cornea, lens, etc.), and identification of specific lesion features. The system will select frames that meet all the screening criteria. If there are multiple frames that meet the criteria, their quality scores will be further compared, and the frames with the highest scores will be selected. Finally, the system will perform image fusion or enhancement processing on these selected frames to generate the final target image.

[0052] In some embodiments, the target video frame interception and the target image acquisition can be achieved in a variety of ways: Optionally, the display system can first use the Laplace operator to calculate the clarity score of each frame; then, apply the image segmentation algorithm to identify the key eye structures in each frame; then, evaluate the integrity and visibility of these structures; then, calculate the comprehensive score of each frame according to the preset weights; finally, select the frame with the highest score as the target image. Optionally, the display system can first use the optical flow algorithm to evaluate the degree of motion between each frame; then, select several consecutive frames with the smallest motion; then, align and superimpose these frames; then, perform contrast enhancement and sharpening on the superimposed image; finally, output the processed image as the target image. It is understandable that other methods can also be used to achieve the interception of the target video frame and the acquisition of the target image, such as using a deep learning model to directly extract the best diagnostic frame from the video, which is not limited here.

[0053] S105 , marking the target image to obtain a detection image and display the detection image.

[0054] The labeling process refers to adding diagnostic-related visual identifiers or annotations to the target image. The test image refers to the final image that contains diagnostic information after the labeling process.

[0055] Specifically, the display system performs this step immediately after obtaining the target image to assist doctors in making a diagnosis. The display system first loads a preset ophthalmic diagnostic model, which includes normal parameters and pathological characteristics of various eye structures. Then, the system uses this model to analyze the target image and identify possible abnormal areas or structures that need to be focused on. Next, the system marks these areas on the image, using contour lines, arrows, or text annotations of different colors. The markings can include information such as the location, size, and morphological characteristics of the abnormal area. At the same time, the system will calculate some quantitative indicators, such as corneal thickness, anterior chamber depth, etc., and mark these values ​​in appropriate locations in the image (such as the blank space in the upper right corner). Finally, the system displays the processed detection image on the display, and will display the original image and the marked image at the same time, which is convenient for doctors to compare and analyze.

[0056] In some embodiments, the marking process of the target image and the display of the detection image can be realized in a variety of ways: Optionally, the display system can first use a pre-trained deep learning model to identify various eye structures in the image; then, according to the morphology and positional relationship of these structures, automatically detect possible abnormalities; then, draw a colored border around the abnormal area and add text descriptions; then, calculate key physiological indicators and generate data tables at the edge of the image; finally, display the marked image in full screen on the touch display, allowing the doctor to zoom and view details by touch. Optionally, the display system can first compare the target image with the historical image database; then, mark the area that is different from the historical record; then, call the expert knowledge base to add possible diagnostic suggestions for the marked area; then, generate an interactive layer system that allows the doctor to switch different types of marks; finally, display the original image and the multi-layer marked image on the dual-screen system at the same time, so that the doctor can conduct a comprehensive analysis. It is understandable that other methods can also be used to realize the marking process of the target image and the display of the detection image, such as using augmented reality technology to overlay diagnostic information on the real-time video stream, which is not limited here.

[0057] In the above embodiments, the basic intelligent acquisition and image optimization process is mainly described. In practical applications, the method can also be combined with functions such as augmented reality display and personalized disease tracking to further improve the comprehensiveness and accuracy of ophthalmic diagnosis.

[0058] The following is a supplement to the scenario of this embodiment.

[0059] Doctor C's intelligent slit lamp microscope system has been upgraded. When reexamining the same patient with diabetic retinopathy, the system can not only intelligently collect high-quality images, but also automatically compare them with the patient's historical examination records. The system uses artificial intelligence algorithms to analyze the differences between the current image and the historical image, and automatically marks the changed areas of the lesion. During the examination, the system can also suggest that Doctor C adjust the examination angle or focal length based on the quality of the real-time collected images. After the examination, the system automatically generates a detailed disease progression report, including quantitative analysis of retinopathy and future risk prediction. These features not only improve the accuracy and efficiency of diagnosis, but also provide patients with a more intuitive and comprehensive description of their condition.

[0060] After combining the above scenarios, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the imaging display method of the slit lamp microscope in the embodiment of the present application.

[0061] S201, acquiring an eye image of a target object, and determining identity information of the target object according to the eye image.

[0062] The eye image refers to a digitized picture containing the patient's eye features. The identity information is used to represent the patient's unique identifier, such as name, ID number or medical record number.

[0063] Specifically, the display system performs this step at the initial stage of the patient's visit to achieve rapid identification and verification of the patient's identity. When the patient sits in the examination position, the display system first activates the camera connected to the slit lamp microscope. The system adjusts the focus and angle of the camera to ensure that the entire eye area of ​​the patient can be clearly captured. Then, the system quickly takes one or more eye images, which include features around the eyes, such as iris texture, eyelid shape, etc. Next, the system uses a pre-trained biometric recognition algorithm to analyze these images and extract unique eye features. Finally, the system matches the extracted features with the patient information stored in the database to determine the patient's identity information, that is, through iris recognition or feature recognition of the corresponding area of ​​the face, the system can determine the patient's identity.

[0064] In some embodiments, the acquisition of the target object's eye image and the determination of identity information can be achieved in a variety of ways: Optionally, the display system can first use a facial detection algorithm to locate the patient's eye position; then, the system adjusts the camera parameters to focus on the eye area; then, the system continuously takes multiple eye images and selects the clearest one; then, the system uses an iris recognition algorithm to extract iris features; finally, the extracted features are compared with the iris feature database to determine the patient's identity. Optionally, the display system can first let the patient look at a moving light spot while capturing the eye movement sequence; then, the system analyzes the eye movement pattern and extracts the individual's unique eye movement features; then, the system matches these features with the pre-stored eye movement pattern database; then, the system combines iris texture and eye movement pattern for multi-modal identity authentication; finally, outputs the identity information with the highest matching degree. It can be understood that other methods can also be used to achieve the acquisition of the target object's eye image and the determination of identity information, such as combining face recognition technology for auxiliary verification, which is not limited here.

[0065] S202: Obtain historical inspection records of the target object according to the identity information.

[0066] Among them, historical examination records refer to detailed information about the patient's past eye examinations, including examination date, diagnosis results, treatment plan, etc.

[0067] Specifically, the display system first establishes a secure connection with the hospital's electronic medical record system, and then uses the patient's identity information (such as ID number or medical record number) as a keyword to send a query request to the database. The database will return all relevant ophthalmic examination records of the patient, including but not limited to past diagnosis results, treatment records, eye images, and examination reports. After receiving this data, the system will initially organize and classify the information, such as arranging the examination records in chronological order, or grouping them according to the type of examination (such as routine examinations, special examinations, etc.). Finally, the system temporarily stores the processed historical examination records in local memory for users to quickly access and subsequent analysis.

[0068] In some embodiments, the acquisition of the historical examination records of the target object can be achieved in a variety of ways: Optionally, the display system can first connect to the central medical database through an encrypted channel; then, the system uses the patient's unique identifier to perform a query operation in the database; then, the system receives the returned raw data and decrypts it locally; then, the system uses natural language processing technology to analyze the text records and extract key diagnostic information; finally, the system associates the extracted information with relevant medical images to form a structured historical examination record. Optionally, the display system can first access a distributed medical data network to obtain the patient's examination records from multiple medical institutions; then, the system unifies the format and resolves conflicts for data from different sources; then, the system uses a machine learning algorithm to analyze the historical data and identify potential disease development trends; then, the system generates a patient's eye health timeline, marking important diagnostic and treatment events; finally, the system presents the processed historical records in a visual form to facilitate doctors to quickly understand the patient's medical history. It is understandable that other methods can also be used to achieve the acquisition of the historical examination records of the target object, such as ensuring the integrity and immutability of historical records through blockchain technology, which is not limited here.

[0069] S203: Generate key focus areas for this inspection based on historical inspection records, and display the key focus areas.

[0070] Among them, the key focus areas indicate the locations or structures of the eyes that require special attention during this eye examination.

[0071] Specifically, the display system performs this step after obtaining historical examination records to assist doctors in conducting more targeted examinations. The display system first analyzes the patient's historical examination records to identify abnormal findings in past diagnoses or areas that require continuous observation. Then, the system evaluates the importance of these areas in this examination based on the development patterns of ophthalmic diseases and clinical guidelines. Next, the system marks these key areas of concern on the virtual eye model, which may include specific corneal areas, lens areas, or retinal areas. The system also adds a brief description of each key area, such as the findings of the last examination and specific features that are recommended for attention. Finally, the system displays this marked virtual eye model on the doctor's operating interface, which can be in a separate window on the main display.

[0072] In some embodiments, the generation and display of the focus area can be achieved in a variety of ways: Optionally, the display system can first use natural language processing technology to analyze historical examination reports and extract keywords and abnormal descriptions; then, the system maps this information to a standardized ocular anatomical model; then, the system assigns priority to each focus area based on the severity and change trend of the abnormality; then, the system generates an interactive 3D eyeball model, and marks the focus area with different colors and shapes on the model; finally, the system allows the doctor to rotate and enlarge the 3D model through a touch screen or gesture operation to view detailed information. Optionally, the display system can first use a machine learning algorithm to analyze the patient's historical image data and identify the areas that have changed; then, the system matches these changes with the pathological development patterns in the clinical knowledge base; then, the system generates a time series visualization chart to show the change trend of the focus area over time; then, the system uses a semi-transparent overlay on the current real-time eye image to mark the focus area; finally, the system provides a voice prompt function to actively remind the doctor to pay attention to specific areas during the examination. It is understandable that other methods can also be used to achieve the generation and display of the focus area, such as using artificial intelligence to predict new areas where problems may occur, which is not limited here.

[0073] S204: After receiving a capture start instruction from the user, obtain a first eye video of the target object using a first resolution.

[0074] Referring to step S101 , the display system acquires a first eye video.

[0075] In some embodiments, after detecting the user's microscope adjustment operation, the display system obtains the current microscope parameter information including magnification, focal length and lighting intensity; obtains the detection process information and pathology reference information of the target object; and uses the HUD display module to display the microscope parameter information, detection process information and pathology reference information in the display light path of the microscope.

[0076] Among them, the microscope adjustment operation refers to the various setting changes made by the doctor to the slit lamp microscope. Microscope parameter information refers to a set of data describing the current working status of the microscope; the detection process information refers to the standard operating procedures for ophthalmic examinations; and the pathology reference information refers to the description of the characteristics of eye lesions related to the current examination. The HUD display module represents the head-up display system, which is used to overlay information in the user's field of view. The display light path refers to the path of light propagation in the microscope, which is used to form an image.

[0077] The display system detects any adjustments made by the doctor to the microscope and performs this operation immediately to provide real-time parameter feedback and auxiliary information. Specifically, when the doctor adjusts any control knob or button of the microscope, the display system immediately obtains the latest parameter data from the microscope's control unit, including the current magnification (such as 10x, 16x, etc.), focal length value (in millimeters), and illumination intensity level. At the same time, the system retrieves the corresponding inspection process guide and related pathology reference materials from the database based on the patient information and examination type. The display system then activates the HUD (head-up display) module and superimposes this information on the optical imaging path of the microscope in a translucent manner. Doctors can see this important information directly in the field of view without changing their line of sight, such as the current magnification, the recommended next inspection operation, and the pathological features that need attention.

[0078] In some embodiments, the acquisition and display of microscope parameter information can be achieved in a variety of ways: Optionally, the display system can first establish a real-time data connection with the microscope control unit; then, the system uses an event listener to continuously monitor parameter changes; then, when a change is detected, the system immediately updates the local parameter cache; then, the system renders the updated parameter information into a graphical interface according to a preset layout template; finally, the system superimposes the rendered graphics into the eyepiece field of view of the microscope through an optical synthesizer. Optionally, the display system can first develop a dedicated microscope parameter acquisition module; then, the module collects various parameters in real time through an analog-to-digital converter; then, the system uses a filtering algorithm to remove noise from parameter fluctuations; then, the system compares the processed parameter data with a pre-stored expert experience database; finally, the system generates optimization suggestions and projects the information to the edge area of ​​the microscope field of view through a micro-projector. It is understandable that other methods can also be used to achieve the acquisition and display of microscope parameter information, such as using augmented reality technology to display parameter information on a doctor's smart glasses, which is not limited here.

[0079] S205: Determine the eye movement trajectory of the target object according to the first eye video.

[0080] Referring to step S102 , the display system determines the eye movement trajectory.

[0081] S206: After determining that the eyes of the target object meet the acquisition condition according to the eye movement trajectory, obtain a second eye video using a second resolution.

[0082] Referring to step S103 , the display system acquires a second eye video.

[0083] In some embodiments, the display system calculates the eyelid stability index of the eyelid movement trajectory and the eyeball stability index of the eyeball movement trajectory; when the eyelid stability index is higher than a first preset threshold and the eyeball stability index is higher than a second preset threshold, the position information of the target object's eye is determined according to the first eye video; after adjusting the shooting focal length and shooting angle of the shooting module according to the position information, the second eye video is obtained using the second resolution.

[0084] Among them, the eyelid movement trajectory refers to the sequence of position changes during the eyelid opening and closing process, and the eyeball movement trajectory refers to the sequence of position changes when the eyeball rotates. The eyelid stability index and eyeball stability index are used to quantify the stability of eye movement.

[0085] Specifically, the display system first performs image processing on each frame in the first eye video to extract the contours of the eyelids and eyeballs. The system then tracks the changes in these contours between consecutive frames to generate the movement trajectories of the eyelids and eyeballs. Next, the system calculates the rate of change and amplitude of these trajectories to derive the eyelid stability index and the eyeball stability index. If these two indexes exceed their respective preset thresholds at the same time, the system considers that the eye has reached a stable state. At this point, the system will accurately locate the position of the eye in the field of view, and adjust the focal length and angle of the shooting module accordingly to ensure that the eye is in the best shooting position. Finally, the system switches to high-resolution microscopic camera mode and starts collecting the second eye video.

[0086] S207 . Capture multiple frame images of the second eye video according to a preset frame interval, and calculate a target area integrity score of the frame image.

[0087] The preset frame interval refers to the time interval for selecting frames in the video sequence. The second eye video refers to an eye examination video shot with high resolution. The frame image refers to a single static image in the video. The target area integrity score is used to measure the integrity and clarity of key eye structures in the frame image.

[0088] Specifically, the display system performs this step after acquiring a high-resolution second eye video to select the best quality frame image. The display system first extracts static images from the second eye video according to a preset frame interval (for example, every 10 frames). The setting of this interval is intended to balance processing efficiency and image quality. The system then preprocesses each extracted frame image, such as denoising and contrast enhancement. Next, the system uses an image segmentation algorithm to identify key eye structures in each frame, such as the cornea, lens, iris, etc. The system evaluates the boundary integrity, area coverage, and clarity of these structures. Based on these factors, the system calculates a comprehensive target area integrity score for each frame image. The score is a value between 0 and 100 that represents the suitability of the frame image for diagnostic purposes.

[0089] In some embodiments, the frame image interception and the target area integrity score calculation can be implemented in a variety of ways: Optionally, the display system can first use an optical flow algorithm to evaluate the degree of motion between adjacent frames and determine the optimal frame interval; then, the system extracts the frame image according to the determined interval; then, the system applies a deep learning model (such as U-Net) to semantically segment each frame and identify key eye structures; then, the system calculates the area ratio and edge clarity of each structure; finally, the system weights and sums the various indicators to obtain the final integrity score. Optionally, the display system can first use a fast Fourier transform to analyze the frequency characteristics of the video and select the frame with the largest amount of information; then, the system applies an adaptive threshold segmentation algorithm to the selected frame to extract the eye contour; then, the system uses morphological operations to optimize the segmentation results; then, the system calculates the similarity between the target area and the ideal template; finally, the system combines the similarity and image clarity indicators to generate a comprehensive integrity score. It can be understood that other methods can also be used to implement the interception of frame images and the calculation of the target area integrity score, such as using a reinforcement learning algorithm to dynamically adjust the frame selection strategy, which is not limited here.

[0090] In some embodiments, the display system captures the image of each frame of the second eye video to obtain a set of original frame images; determines the original frame images in the set of original frame images whose clarity is lower than a preset clarity threshold as the frame images to be optimized, and determines the pixel blocks to be optimized of the frame images to be optimized; obtains a preset number of preceding frame images and following frame images of the frame images to be optimized; completes the pixel blocks to be optimized of the frame images to be optimized based on the preceding frame images and the following frame images to obtain an optimized frame image; replaces the frame images to be optimized in the set of original frame images with the optimized frame images to obtain the optimized second eye video.

[0091] The original frame image set represents all single frame images extracted from the second eye video. The clarity threshold refers to the standard value for judging whether an image needs to be optimized. The frame image to be optimized refers to an image that needs to be improved due to insufficient clarity, and the pixel block to be optimized represents an area in the image that needs to be processed due to low quality. The pre-frame image and post-frame image refer to high-quality images before and after the frame to be optimized.

[0092] Specifically, the display system performs this operation after acquiring the second eye video to improve the overall video quality. The display system first decomposes the second eye video into a series of separate frame images to form a set of original frame images. Then, the system evaluates the clarity of each frame image using methods such as gradient amplitude and spectrum analysis. For frames whose clarity is lower than a preset threshold, the system marks them as frames to be optimized, and further analyzes the areas with poor quality in these frames to identify the pixel blocks to be optimized. Next, the system selects several frames of high-quality images before and after the frame to be optimized as references. The system uses the information of these reference frames to improve the low-quality areas in the frame to be optimized through interpolation, super-resolution reconstruction and other techniques. Finally, the system replaces the original low-quality frames with the processed high-quality frames to obtain an eye video with higher overall quality.

[0093] In some embodiments, the optimization processing of video frames can be achieved in a variety of ways: Optionally, the display system can first use the Laplace operator to calculate the clarity score of each frame; then, apply the wavelet transform to the frames below the threshold to identify the frequency components that need to be optimized; then, extract the corresponding frequency information from the adjacent high-quality frames; then, use the weighted average method to fuse the original information and the supplementary information; finally, perform an inverse wavelet transform to reconstruct the optimized frame image. Optionally, the display system can first use a deep learning model to evaluate the quality of each frame; then, use the optical flow algorithm for low-quality frames to calculate the pixel correspondence between the high-quality frames; then, apply a patch-based super-resolution algorithm to reconstruct the low-quality area; then, use an edge-preserving filter to smooth the reconstruction result; finally, seamlessly integrate the reconstructed area into the original frame. It is understandable that other methods can also be used to achieve the optimization processing of video frames, such as using a generative adversarial network (GAN) to repair and enhance low-quality frames, which is not limited here.

[0094] S208 , filter out frame images whose target area integrity scores are not less than a preset integrity threshold to obtain candidate frames.

[0095] The preset integrity threshold refers to the minimum acceptable target region integrity score predefined by the system. The candidate frame refers to a frame that has passed preliminary screening and is considered to be a final diagnostic image.

[0096] Specifically, the display system performs this step immediately after calculating the target area integrity scores of all frame images to narrow the range of images that need further analysis. The display system first sets a preset integrity threshold based on clinical needs and image quality standards. This threshold can be determined and set by ophthalmologists and image analysis experts. Then, the system compares the integrity score of each frame image with this threshold. Only frame images with a score not lower than the threshold will be retained. The system will create a new image set and add all qualified frames to this set to form a candidate frame set. At the same time, the system will also record the original position information and integrity score of each candidate frame for subsequent analysis. Finally, the system will preliminarily sort the candidate frame set in preparation for the next step of processing.

[0097] S209 , performing feature point matching on the candidate frames, and selecting N target video frames with the highest feature point matching degree.

[0098] Among them, feature points refer to points with unique properties in the image, such as corner points or edge points. Feature point matching refers to the process of finding corresponding feature points between different frames. The matching degree is used to measure the accuracy of the correspondence between feature points between different frames. The N target video frames refer to the high-quality frame images finally selected for subsequent processing.

[0099] Specifically, the display system first applies a feature point detection algorithm, such as SIFT (Scale Invariant Feature Transform) or SURF (Speeded Up Robust Features) algorithm, to each candidate frame to extract key points in the image. The system then matches feature points between different candidate frames using methods such as nearest neighbor matching or ratio testing. The system calculates the number of matching points and the quality of matching between each pair of candidate frames to generate a matching matrix. Next, the system analyzes this matrix to identify frames that are highly consistent with other frames. Based on this analysis, the system selects the N frames with the highest feature point matching as the target video frames. Here, N is a preset value, which can be 3, 5, or more, depending on the needs of subsequent processing.

[0100] In some embodiments, feature point matching and target video frame selection can be achieved in a variety of ways: Optionally, the display system can first use the ORB (Oriented FAST and Rotated BRIEF) algorithm to quickly extract feature points of candidate frames; then, the system uses the Hamming distance to calculate the similarity between feature descriptors; then, the system applies the RANSAC algorithm to eliminate false matches; then, the system calculates the average matching score of each frame with all other frames; finally, the system selects the N frames with the highest scores as target video frames. Optionally, the display system can first use a deep learning model to extract more robust feature points; then, the system uses a graph matching algorithm to build a similarity graph between frames; then, the system applies a spectral clustering method to group frames; then, the system selects the frames closest to the group center from each group; finally, the system selects the N most feature-rich frames from these representative frames as target video frames. It is understandable that other methods can also be used to achieve feature point matching and target video frame selection, such as using spatiotemporal consistency constraints to improve matching accuracy, which is not limited here.

[0101] S210 , performing image fusion on N target video frames to obtain a target image.

[0102] Among them, image fusion refers to the process of merging the information of multiple images into a single image.

[0103] Specifically, the display system first preprocesses N target video frames, including image registration and illumination equalization. Registration ensures that the eye structures in all frames are located in the same position, and illumination equalization eliminates the brightness differences between different frames. Then, the system uses multi-resolution decomposition to decompose each frame into different frequency components. Next, the system applies fusion rules on each frequency layer, such as taking the maximum value, weighted average, or saliency-based selection. For low-frequency components, the system uses weighted averaging to maintain overall brightness and contrast; for high-frequency components, the system selects the clearest or most prominent details. Finally, the system recombines the fused frequency components to obtain the final target image. This target image contains the best features of all input frames.

[0104] In some embodiments, the image fusion of N target video frames can be achieved in a variety of ways: Optionally, the display system can first use the optical flow method to accurately align the N target video frames; then, the system applies wavelet transform to decompose each frame into multiple sub-bands; then, the system uses regional energy-based fusion rules on each sub-band; then, the system performs inverse wavelet transform on the fused sub-band coefficients; finally, the system performs post-processing on the reconstructed image, such as sharpening and denoising, to obtain the final target image. Optionally, the display system can first use a deep learning model (such as U-Net) to semantically segment each frame; then, the system assigns different fusion weights to each region based on the segmentation results; then, the system performs weighted fusion in a multi-scale pyramid domain; then, the system uses guided filtering to optimize the fusion boundary; finally, the system applies contrast-limited adaptive histogram equalization to enhance the visual effect of the fused image and generate the target image. It is understandable that other methods can also be used to achieve image fusion of N target video frames, such as using tensor decomposition technology to process high-dimensional image data, which is not limited here.

[0105] S211, marking the target image to obtain a detection image and display the detection image.

[0106] Referring to step S105 , the display system will display the detection image.

[0107] In some embodiments, the display system stores the detection image in the historical inspection record; obtains the pathological diagnosis information input by the user; generates a pathological development report of the target object based on the historical inspection record, the detection image and the pathological diagnosis information, and displays the pathological development report.

[0108] Among them, pathological diagnosis information represents the doctor's professional judgment on the results of this examination. Pathological development report refers to the disease progression analysis document generated by integrating historical and current information.

[0109] Specifically, the display system first stores the test images obtained from this examination into the patient's electronic medical record system and updates the historical examination records. Then, the diagnosis information entered by the doctor is collected through the user interface, which may include disease type, severity, treatment recommendations, etc. Next, the system calls the data analysis module to compare the new test images with historical images to quantify changes in key indicators. At the same time, the system integrates historical diagnostic records, current diagnosis and image analysis results, and uses a preset report template to generate a detailed pathology development report. This report can include a disease progression timeline, a chart of changes in key indicators, current status assessments, and future development forecasts. Finally, the system presents the report on the display for the doctor to review and explain to the patient.

[0110] In some embodiments, the generation and display of the pathology development report can be achieved in a variety of ways: Optionally, the display system can first use image registration technology to align historical and current eye images; then, apply an image difference algorithm to highlight the changed area; then, use a machine learning model to analyze the nature and extent of the change; then, match the analysis results with the disease progression pattern in the medical knowledge base; finally, generate an interactive report containing visual charts and text descriptions. Optionally, the display system can first build a personalized eye health digital twin model for the patient; then, input new examination data into the model to update the disease progression trajectory; then, use natural language processing technology to convert the model output into an easy-to-understand narrative report; then, apply data visualization technology to create an intuitive disease progression chart; finally, display the report through a multimedia interface, allowing doctors and patients to interact in depth. It is understandable that other methods can also be used to achieve the generation and display of pathology development reports, such as using augmented reality technology to overlay lesion progression information on real eye images, which is not limited here.

[0111] In the embodiments of the present application, due to the use of innovative technologies such as intelligent hierarchical image acquisition, real-time eye movement analysis, adaptive resolution adjustment, and multi-frame image fusion, it is possible to intelligently capture the best imaging time when the eyeball moves slightly, and generate high-quality diagnostic images through efficient image processing algorithms, effectively solving the image blur and storage resource waste problems of traditional slit lamp microscopes when dealing with involuntary eye movements of patients, thereby achieving a more efficient and accurate ophthalmic examination process. In addition, this method also integrates functions such as historical data comparison, intelligent diagnostic assistance, and personalized report generation, which improves the comprehensiveness and accuracy of ophthalmic diagnosis, provides doctors with a more comprehensive diagnostic basis, and also provides patients with a more intuitive and easier to understand description of the condition, improving the user experience.

[0112] The following describes the display system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of a display system in an embodiment of the present application.

[0113] It should be noted that Figure 3 The structure of the display system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0114] like Figure 3As shown, the display system 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 part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, the ROM 302 and the RAM 303 are connected to each other through the bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0115] 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) and 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 therefrom is installed into the storage section 308 as needed.

[0116] In particular, 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 a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0117] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0118] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0119] Specifically, the display system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the imaging display method of the slit lamp microscope provided in the above embodiment is implemented.

[0120] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the display system described in the above embodiment; or may exist independently without being assembled into the display system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the display system, the display system implements the imaging display method of the slit lamp microscope provided in the above embodiment.

[0121] As described 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, 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 embodiments of the present application.

[0122] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0123] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. An imaging display method for a slit lamp microscope, characterized in that: Applied to a display system, the method comprises: After receiving a capture start instruction from the user, acquiring a first eye video of the target object using a first resolution; determining an eye movement trajectory of the target object according to the first eye video; After determining that the eyes of the target object meet the acquisition condition according to the eye movement trajectory, acquiring a second eye video using a second resolution; the second resolution is higher than the first resolution; Intercepting a target video frame that meets the detection requirement in the second eye video to obtain a target image; The target image is marked to obtain a detection image and the detection image is displayed.

2. The method according to claim 1, characterized in that The eye movement trajectory includes an eyelid movement trajectory and an eyeball movement trajectory; after determining that the eyes of the target object meet the acquisition condition according to the eye movement trajectory, obtaining a second eye video using a second resolution specifically includes: Calculating an eyelid stability index of the eyelid movement trajectory and an eyeball stability index of the eyeball movement trajectory; When the eyelid stability index is higher than a first preset threshold and the eyeball stability index is higher than a second preset threshold, determining the position information of the eye of the target object according to the first eye video; After adjusting the shooting focal length and shooting angle of the shooting module according to the position information, a second eye video is acquired using a second resolution.

3. The method according to claim 1, characterized in that The step of intercepting a target video frame that meets the detection requirement in the second eye video to obtain a target image specifically includes: intercepting a plurality of frame images of the second eye video according to a preset frame interval, and calculating a target area integrity score of the frame images; Filter out the frame images whose integrity scores of the target regions are not less than a preset integrity threshold to obtain candidate frames; Perform feature point matching on the candidate frames, and select N target video frames with the highest feature point matching degree; The N target video frames are subjected to image fusion to obtain a target image.

4. The method according to claim 3, characterized in that Before the step of intercepting a plurality of frame images of the second eye video at a preset frame interval and calculating the target area integrity score of the frame image, the method further includes: Intercepting an image of each frame of the second eye video to obtain an original frame image set; Determine, in the original frame image set, an original frame image whose definition is lower than a preset definition threshold as a frame image to be optimized, and determine a pixel block to be optimized of the frame image to be optimized; Acquire a preset number of preceding frame images and following frame images of the frame image to be optimized; According to the preceding frame image and the succeeding frame image, the pixel blocks to be optimized of the frame image to be optimized are completed to obtain an optimized frame image; The frame image to be optimized in the original frame image set is replaced with the optimized frame image to obtain a second eye video after optimization.

5. The method according to claim 1, characterized in that: Before the step of acquiring a first eye video of the target object using the first resolution, the method further includes: Acquire an eye image of a target object, and determine identity information of the target object based on the eye image; According to the identity information, obtaining the historical inspection record of the target object; Based on the historical inspection records, a key focus area for this inspection is generated, and the key focus area is displayed.

6. The method according to claim 5, characterized in that After the step of marking the target image to obtain a detection image and displaying the detection image, the method further includes: storing the detected image in the historical inspection record; Acquiring pathological diagnosis information input by the user; A pathology development report of the target object is generated according to the historical inspection records, the detection images and the pathology diagnosis information, and the pathology development report is displayed.

7. The method according to claim 1, characterized in that The display system includes a HUD display module; before the step of acquiring a first eye video of the target object using a first resolution, the method further includes: After detecting the user's microscope adjustment operation, obtaining current microscope parameter information including magnification, focal length and illumination intensity; Obtain the detection process information and pathological reference information of the target object; The HUD display module is used to display the microscope parameter information, the detection process information and the pathology reference information in the display light path of the microscope.

8. A display system, characterized in that: The display system 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 display system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a display system, the display system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is executed on a display system, the display system is caused to execute the method according to any one of claims 1 to 7.

Images