Slit lamp detection light intensity determination method, storage medium and electronic equipment
By collecting and calibrating pupil change sequences and combining them with a classification model to determine the light intensity of the slit lamp detection light, the problem of balancing light intensity and human eye safety in slit lamp detection was solved, achieving safe and efficient detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SUZHOU JUNXIN SHIDA MEDICAL TECH CO LTD
- Filing Date
- 2025-11-10
- Publication Date
- 2026-04-21
AI Technical Summary
In slit-lamp inspection, existing technologies have failed to effectively balance light intensity with human eye safety, potentially causing damage to the human eye.
By acquiring eye images at different time steps, a pupil change sequence is generated. The pupil diameter is calibrated using ambient light and flicker frequency correction coefficients. The maximum light intensity that the human eye can tolerate is determined by combining a classification model, and the light intensity of the slit lamp detection light is generated.
It achieves the goal of ensuring detection clarity while avoiding damage to the human eye from light intensity, providing an accurate light intensity tolerance threshold for the human eye, and adapting to different ambient light conditions.
Smart Images
Figure CN121890935A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of slit lamp detection technology, and in particular to a method for determining the light intensity of slit lamp detection light, a storage medium, and an electronic device. Background Technology
[0002] In ophthalmic clinical examinations, the slit-lamp biomicroscope is one of the most essential and commonly used examination instruments, used to observe the fine structures of the anterior segment (cornea, anterior chamber, iris, lens, etc.). During a slit-lamp examination, the chin is rested on a chin rest, the forehead is pressed against the forehead rest, and the head is kept stable and still. For some routine examinations, natural light shining on the eyeball is sufficient to obtain the corresponding images. In some specialized examinations, a beam of slit light is projected onto the eyeball to obtain clear, stable, and diagnostically valuable images.
[0003] When slit light (detection light) is shone onto the human eye for observation, different individuals exhibit varying degrees of reaction and tolerance to light intensity. In practical applications, two core requirements must be met simultaneously: first, ensuring sufficient clarity of illumination to meet examination needs; and second, avoiding excessive light intensity that could damage the human eye. Currently, insufficient attention is paid to "avoiding eye damage" in detection processes, and detection light can easily cause eye injury during examinations. Summary of the Invention
[0004] To address one of the aforementioned technical problems, the present invention adopts the following technical solution: According to one aspect of the present invention, a method for determining the intensity of slit lamp detection light is provided, the method comprising the following steps: The human eye is illuminated with a slit light of preset intensity, and eye images are acquired at different time steps during the illumination process; the illumination duration and extinguishing duration are the same within one flash cycle of the slit light, and eye images are acquired during the extinguishing period of one flash cycle. Based on the eye image at each moment, obtain the pupil diameter corresponding to each moment to form an initial pupil change sequence; Based on the current ambient light intensity L env The pupil diameter in the initial pupil change sequence is corrected by the slit light scintillation frequency F to generate the target pupil change sequence. The corrected diameter D of the i-th pupil jz i satisfies the following condition: D jz i=D cs i×K env ×K freq ; ; ; Among them, D cs i is the pupil diameter of the i-th pupil in the initial pupil change sequence; K env and K freq These are the ambient light correction factor and the frequency correction factor, respectively; L ref β is the preset reference ambient light intensity; ϵ is the scaling factor; k is the smoothing constant; f0 is the adjustment factor; and f0 is the preset half-fade flicker frequency. Input the target pupil change sequence into the target classification model to generate the maximum light intensity that the human eye can tolerate. The slit lamp detection light intensity is generated based on the maximum tolerated light intensity and the minimum detection light intensity.
[0005] Furthermore, the scintillation frequency F of the slit light is obtained according to the following steps; According to L env The total exposure Q is used to generate the exposure duration T; T satisfies the following condition: T = Q / L env ; Based on T, generate F, where F satisfies the following condition: ; Where Tmax is the maximum extinction duration.
[0006] Furthermore, the human eye is illuminated with slit light of a preset intensity, including: Different slit lights of varying intensities are used to form different irradiation groups, which are then used to irradiate the human eye in sequence. A recovery interval is set between adjacent irradiation groups.
[0007] Furthermore, based on the eye image at each moment, the pupil diameter at each moment is obtained, including: Image recognition technology is used to identify the pupil region in each eye image in order to generate the corresponding pupil diameter.
[0008] Furthermore, the target classification model includes supervised learning classifiers and / or K-Means classification algorithms.
[0009] Furthermore, supervised learning classifiers include: SVM, random forest, XGBoost, or neural networks.
[0010] Furthermore, based on the maximum tolerated light intensity and the minimum detection light intensity, the slit lamp detection light intensity is generated, including: If the maximum tolerated light intensity is less than or equal to the minimum detection light intensity, then the minimum detection light intensity will be used as the slit lamp detection light intensity.
[0011] Furthermore, based on the maximum tolerated light intensity and the minimum detection light intensity, the slit lamp detection light intensity is generated, including: If the maximum tolerated light intensity is greater than the minimum detection light intensity, then any light intensity within the range from the maximum tolerated light intensity to the minimum detection light intensity will be used as the slit lamp detection light intensity.
[0012] According to a second aspect of the present invention, a non-transitory computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the above-described method for determining the intensity of slit lamp detection light.
[0013] According to a third aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for determining the intensity of slit lamp detection light.
[0014] This invention has at least one of the following beneficial effects: This invention collects data on the changes in pupil diameter at different times under a certain light intensity, forming a corresponding sequence to reflect the pupil constriction amplitude (difference between maximum and minimum diameter), pupil constriction speed (rate of diameter change), and human eye reaction speed (time interval from the start of light exposure to pupil constriction) under that light intensity. Since these parameters can represent the different degrees of human eye responses under that light intensity, and individuals with similar or comparable tolerance levels typically react similarly to the same light intensity, the pupil diameter data at different time points are used to form a feature vector. A classification algorithm is then used to determine the human eye's tolerance threshold to light intensity.
[0015] Meanwhile, the initial size and constriction range of the pupil are affected by ambient light. Specifically, the stronger the ambient light, the smaller the initial pupil diameter and the smaller the constriction range in response to the test light; conversely, the weaker the ambient light, the smaller the constriction range. Therefore, different adjustment coefficients are needed to calibrate the pupillary response parameters to standardize the parameter scale under different environments. For example, the magnification coefficient is set to 1.5 under strong light and 1 under weak light. Ultimately, this eliminates the influence of ambient light on the variable range of the pupil, making the parameters comparable under different environments.
[0016] Furthermore, to eliminate interference from the test light during pupil identification, this invention employs flashing light for illumination. During each flashing cycle, the pupil constricts during the illumination phase and may dilate during the exposure phase due to the cessation of illumination. Therefore, an algorithm is used to eliminate the error of non-light intensity-induced pupil dilation during the exposure phase, retaining only the true constriction parameters under light stimulation. In this invention, when the frequency decreases due to ambient light adjustment, a reduction factor is used to eliminate the frequency's interference with sensitivity, ensuring that the detection results only reflect the effect of light intensity on the pupil. This allows the calibrated multi-timepoint pupil diameter data to form a more accurate feature vector, ensuring that the output of the classification algorithm yields a more accurate maximum light intensity threshold tolerable by the human eye. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 A flowchart illustrating a method for determining the intensity of slit lamp detection light according to an embodiment of the present invention; Figure 2 During slit-lamp examination, the image of light shining on the eyeball is detected. Detailed Implementation
[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0020] As one possible embodiment of the present invention, such as Figure 1 As shown, a method for determining the intensity of slit lamp detection light is provided, which includes the following steps: S100: Illuminates the human eye using slit light of preset intensity and acquires eye images at different time steps during the illumination process. The illumination duration and extinguishing duration are the same within one flicker cycle of the slit light, and eye images are acquired during the extinguishing period of one flicker cycle.
[0021] Specifically, S100 uses slit light of preset intensity to illuminate the human eye, including: S101: Using slit light of different intensities, different irradiation groups are formed to irradiate the human eye in sequence, and a recovery interval is set between two adjacent irradiation groups.
[0022] In daily life, the light intensity (illuminance, measured in lux) that provides a comfortable and fatigue-free experience for the human eye is typically between 300 and 1000 lux. For example, 300-500 lux is recommended for offices, 500-750 lux for classrooms, and above 500 lux for intensive reading or work. In this embodiment, during slit-light detection, strong light is directly shone into the eyes. Therefore, exposure to light exceeding 1000 lux can typically cause eye discomfort and damage.
[0023] In this embodiment, according to the tolerance range of the human eye to light intensity (such as 1000 lux to 50000 lux), the preset light intensity is divided into 5 gradient irradiation groups, and the light intensity of each group increases from low to high, avoiding excessive pupil contraction caused by initial strong light stimulation. The light intensity difference between adjacent groups is controlled within 1.5 to 2 times, ensuring that the tolerance threshold critical point can be accurately captured.
[0024] Specifically, in this embodiment, the irradiation groups can be set in the form shown in Table 1 below: Table 1 Through the design of "low → high gradient light intensity + recovery interval", it not only avoids potential damage to the human eye caused by single strong light, but also ensures that the pupil responses under each light intensity stimulation are independent and real, providing a data basis for the accuracy of the subsequent "initial pupil change sequence". For example, if the 6000 lux of Group 3 causes a severe pupil contraction, it can be preliminarily judged that its tolerance threshold is close to this light intensity, and subsequent Groups 4, 5, and 6 can further verify it.
[0025] In addition, as Figure 2 shown, since the detection beam and the through-hole are usually superimposed, and the eye image is obtained during the lighting duration, the image of the beam will interfere with the subsequent image recognition of the through-hole. Therefore, in this step, the eye image is obtained during the extinguishing period of the flashing cycle.
[0026] S200: According to the eye image at each moment, obtain the corresponding pupil diameter at each moment to form an initial pupil change sequence.
[0027] S200 includes: S201: Use image recognition technology to identify the pupil area in each eye image to generate the corresponding pupil diameter.
[0028] Specifically, first convert the color eye image into a grayscale image to reduce the calculation amount, enhance the gray difference between the pupil and the iris through Contrast Limited Adaptive Histogram Equalization (CLAHE). The pupil area usually has a low gray value, and the iris has a medium to high gray value, eliminating the interference of local shadows caused by uneven ambient light.
[0029] Then perform threshold segmentation: Determine the dual thresholds (T1, T2) based on the gray histogram, where T1 is the pupil-iris boundary threshold, usually taking the value of the 5% to 10% area with the lowest gray value, and T2 is the iris-sclera boundary threshold to exclude the sclera area with high gray values. Extract the suspected pupil area through binarization, that is, the connected area with pixel value < T1.
[0030] Next, edge detection and morphological optimization are performed: the Canny edge detection algorithm is used to extract contours from the binarized image, and contours with an area within a preset range (e.g., 500~5000 pixels, dynamically adjusted according to the resolution of the eye image) and approximately circular (roundness > 0.8) are selected, while false contours such as tear puncta and reflective points are excluded.
[0031] Finally, the minimum circumcircle is fitted to obtain the diameter: for the segmented pupil contour, the least squares method is used to fit the circumcircle, and the diameter of the circle is the initial value of the pupil diameter.
[0032] S300: Based on the current ambient light intensity L env The pupil diameter in the initial pupil change sequence is corrected by the slit light scintillation frequency F to generate the target pupil change sequence.
[0033] The corrected diameter D of the i-th pupil jz i satisfies the following condition: D jz i=D cs i×K env ×K freq .
[0034] .
[0035] .
[0036] Among them, D cs i represents the pupil diameter of the i-th pupil in the initial pupil change sequence. K env and K freq These are the ambient light correction factor and the frequency correction factor, respectively. ref The preset reference ambient light intensity is denoted as β, which is a scaling factor ranging from 0.2 to 0.5. ϵ is a smoothing constant; to avoid a denominator of zero or log(0), ϵ can be 1 lux. k is an adjustment factor, and f0 is the preset half-fade flicker frequency.
[0037] Based on the physiological basis of the human eye, we know that the human eye's perception of light intensity is not linear, but rather logarithmic or approximately logarithmic. Pupil responses also follow a similar pattern: in a dark environment (10 lux), changes in pupil diameter are highly sensitive to changes in light intensity. In a bright environment (10000 lux), the pupil has already constricted to its limit; further increases in light intensity result in almost no change in diameter. Therefore, modeling the ambient light calibration coefficient using a logarithmic function aligns with the physiological response characteristics of the human eye.
[0038] Furthermore, the stronger the ambient light, the smaller the initial pupil diameter, the smaller the space for pupil contraction, and the larger the required magnification factor; conversely, the weaker the ambient light, the greater the magnification. Therefore, calibration is performed based on ambient light, specifically, based on the independent variable... It can be seen that when Lenv =L ref When the ratio is 1, the corresponding log(1) = 0, K env =1, no calibration required. When L env >L ref When the ratio is greater than 1, the corresponding Increase, K env >1, enlarge the diameter value. When L env <L ref When the ratio is less than 1, the corresponding If K is negative, env If the value is less than 1, the diameter value is reduced. This corrects the initial diameter and unifies the comparison scale.
[0039] In addition, because low-frequency flicker causes rhythmic fluctuations in the pupil, this embodiment acquires eye images during the off period and has a certain exposure waiting time. Therefore, since the area is in a state of no light, the pupil will dilate to adapt to the dark environment, resulting in the pupil in the captured image being larger than the diameter when illuminated. Therefore, correction based on flicker frequency is required.
[0040] Because the human eye's perception of flicker is not "on-off," but rather progressively sensitive—for example, 50Hz is very uncomfortable, 80Hz is slightly uncomfortable, and 130Hz is basically imperceptible—using the smooth transition of the sigmoid function is more in line with the continuous response characteristics of biological systems.
[0041] Specifically, K can be controlled based on the choices of f0 and k. freg The size, in addition, can be changed The two values of 0.5 in the formula are used to change K. freg The upper and lower limits, specifically in this embodiment, are K. freg The upper and lower limits are limited to [0.5, 1]. As can be seen from the formula, when F gradually approaches higher frequencies, that is, when F → +∞, K... freg As F gradually approaches 1.0 and the frequency F gradually decreases, that is, when F → 0, K freg It gradually approaches 0.5. Since a lower F-number results in a longer extinction period, a longer exposure wait time, and a greater degree of pupil recovery, a larger reduction in size is needed for correction; conversely, a higher F-number results in the opposite. Therefore, the above correction formula can meet this requirement.
[0042] S400: Input the target pupil change sequence into the target classification model to generate the maximum light intensity that the human eye can tolerate.
[0043] Specifically, the target classification model includes supervised learning classifiers and / or K-Means classification algorithms. Supervised learning classifiers include SVM, random forest, XGBoost, or neural networks. The aforementioned supervised learning classifiers can obtain training samples through the following method: recruit 200 healthy subjects of different ages (18-65 years old), apply gradient light intensity stimulation using a slit lamp in a controlled light environment laboratory according to the S100 to S300 sequence, and obtain pupil diameter change sequences. Individual light intensity tolerance thresholds are determined through subjective feedback combined with fundus camera detection. Finally, a dataset containing labeled samples is constructed, covering different genders, refractive states, and eye health conditions.
[0044] In addition, supervised learning classifiers and K-Means classification algorithms can be combined to generate the maximum light intensity that the human eye can tolerate.
[0045] Specifically, for all calibrated feature vectors (i.e., target pupil change sequences) in the training samples, K-means clustering (e.g., K=3-5) is used, and for each cluster, a separate regression model (e.g., linear regression, SVR, XGBoost) is trained to predict the threshold.
[0046] During prediction: First, use K-means to determine which cluster the new sample belongs to, and then use the regression model of the corresponding cluster to predict the threshold.
[0047] Specifically, in this embodiment, the light intensity of light illuminating the human eye is generally expressed in lux, while the luminous intensity of the slit lamp is measured in candela. This allows the establishment of a mapping table between the light intensity of light illuminating the human eye and the luminous intensity of the slit lamp, so as to quickly obtain the light intensity value of the slit lamp detection light.
[0048] S500: Generates slit lamp detection light intensity based on the maximum tolerated light intensity and the minimum detection light intensity.
[0049] Specifically, the S500 includes: S501: If the maximum tolerated light intensity is less than or equal to the minimum detection light intensity, then the minimum detection light intensity shall be used as the slit lamp detection light intensity.
[0050] S502: If the maximum tolerated light intensity is greater than the minimum detection light intensity, then any light intensity within the range of the maximum tolerated light intensity to the minimum detection light intensity shall be used as the slit lamp detection light intensity.
[0051] In this embodiment, the changes in pupil diameter at different times under a certain light intensity are collected to form a corresponding sequence, reflecting the pupil constriction amplitude (difference between maximum and minimum diameter), pupil constriction speed (rate of diameter change), and human eye reaction speed (time interval from the start of light exposure to pupil constriction) under that light intensity. Since these parameters can represent the different degrees of human eye response under that light intensity, and individuals with similar or comparable tolerance levels typically react similarly to the same light intensity, the pupil diameter data at different time points are used to form a feature vector, which is then used in a classification algorithm to determine the human eye's tolerance threshold to light intensity.
[0052] As another possible embodiment of the present invention, the scintillation frequency F of the slit light is obtained according to the following steps.
[0053] S600: According to L env The total exposure Q is used to generate the exposure duration T. T satisfies the following condition: T = Q / L env .
[0054] In real-world scenarios, exposure = aperture × shutter speed (exposure time) × ISO. However, in this embodiment, since the captured eye images will undergo style recognition processing of the pupils in post-processing, to improve recognition accuracy, it is desirable to obtain a series of photos where, apart from variations in the pupil image, other image qualities remain as consistent as possible, such as image brightness, noise levels, and depth of field. Therefore, to actively control the consistency of "depth of field" and "image quality," this embodiment requires fixing the aperture and ISO, leaving the responsibility of exposure adjustment entirely to the shutter speed. Thus, in this scenario, T = Q / L. env .
[0055] S700: Generate F based on T, where F satisfies the following condition: .
[0056] Where Tmax is the maximum extinction duration.
[0057] In this invention, the slit light employs an alternating illumination-exposure control mechanism. During the illumination phase, only test light is emitted to stimulate pupil contraction (no image acquisition is performed), while during the exposure phase, illumination is stopped and image acquisition relies on ambient light. This separation of illumination and exposure avoids overexposure caused by direct test light, ensuring clarity by using only ambient light for imaging; it also prevents interference from the test light image during pupil recognition.
[0058] When determining the length of the off period, the main consideration is to ensure a sufficiently long exposure time (adequate light intake) to obtain a clear image. Given a consistent total light intake, the exposure time is directly related to the intensity of the ambient light. Therefore, the Q / L ratio can be used to determine the exposure duration. envTo calculate the length of the off period, and because too low a flicker frequency can also cause eye fatigue and damage, a higher flicker frequency needs to be set. This limits the minimum value of the flicker frequency, thereby adaptively adjusting the length of the extinguishing period according to different ambient light intensities, and thus adjusting the flicker frequency to ensure that clear, high-quality images can still be obtained under different ambient light conditions, thereby improving the subsequent image recognition effect.
[0059] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.
[0060] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.
[0061] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.
[0062] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: entirely in hardware, entirely in software (including firmware, microcode, etc.), or in a combination of hardware and software, collectively referred to herein as “circuit,” “module,” or “system.”
[0063] An electronic device according to this embodiment of the invention. The electronic device is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the invention.
[0064] Electronic devices are manifested in the form of general-purpose computing devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and buses connecting different system components (including memory and processor).
[0065] The memory stores program code that can be executed by a processor, causing the processor to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of the present invention.
[0066] The storage may include readable media in the form of volatile storage, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).
[0067] The storage may also include programs / utilities having a set (at least one) of program modules, including but not limited to: an operating system, one or more applications, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.
[0068] A bus can represent one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus that uses any of the various bus architectures.
[0069] The electronic device can also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication can be performed via input / output (I / O) interfaces. Furthermore, the electronic device can communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0070] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the present invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the present invention described in the "Exemplary Methods" section above.
[0071] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0072] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.
[0073] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.
[0074] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java and C++, and conventional procedural programming languages such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).
[0075] Furthermore, the accompanying drawings are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention and are not intended to be limiting. It is readily understood that the processes shown in the above drawings do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.
[0076] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.
[0077] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A method for determining the intensity of a slit lamp detection light, characterized in that, The method includes the following steps: The human eye is illuminated with a slit light of preset intensity, and eye images are acquired at different time steps during the illumination process; the illumination duration and extinguishing duration are the same within one flashing cycle of the slit light, and the eye images are acquired during the extinguishing period of one flashing cycle. Based on the eye image at each moment, obtain the pupil diameter corresponding to each moment to form an initial pupil change sequence; Based on the current ambient light intensity L env The pupil diameter in the initial pupil change sequence is corrected by the slit light flicker frequency F to generate the target pupil change sequence. The corrected diameter D of the i-th pupil jz i satisfies the following condition: D jz i=D cs i×K env ×K freq ; ； ； Among them, D cs i is the pupil diameter of the i-th pupil in the initial pupil change sequence; K env and K freq These are the ambient light correction factor and the frequency correction factor, respectively; L ref β is the preset reference ambient light intensity; ϵ is the scaling factor; k is the smoothing constant; f0 is the adjustment factor; and f0 is the preset half-fade flicker frequency. The target pupil change sequence is input into the target classification model to generate the maximum light intensity that the human eye can tolerate. The slit lamp detection light intensity is generated based on the maximum tolerated light intensity and the minimum detection light intensity.
2. The method according to claim 1, characterized in that, The scintillation frequency F of the slit light is obtained according to the following steps; According to L env The total exposure Q is used to generate the exposure duration T; T satisfies the following condition: T = Q / L env ; Based on T, generate F, where F satisfies the following condition: ； Where Tmax is the maximum extinction duration.
3. The method according to claim 1, characterized in that, Illuminating the human eye with slit light of a preset intensity includes: Different slit lights of varying intensities are used to form different irradiation groups, which are then used to irradiate the human eye in sequence. A recovery interval is set between adjacent irradiation groups.
4. The method according to claim 1, characterized in that, Based on the eye image at each moment, obtain the pupil diameter corresponding to each moment, including: Image recognition technology is used to identify the pupil region in each eye image in order to generate the corresponding pupil diameter.
5. The method according to claim 1, characterized in that, The target classification model includes a supervised learning classifier and / or the K-Means classification algorithm.
6. The method according to claim 5, characterized in that, The supervised learning classifier includes: SVM, random forest, XGBoost, or neural network.
7. The method according to claim 1, characterized in that, The slit lamp detection light intensity is generated based on the maximum tolerated light intensity and the minimum detection light intensity, including: If the maximum tolerated light intensity is less than or equal to the minimum detection light intensity, then the minimum detection light intensity shall be used as the slit lamp detection light intensity.
8. The method according to claim 1, characterized in that, The slit lamp detection light intensity is generated based on the maximum tolerated light intensity and the minimum detection light intensity, including: If the maximum tolerated light intensity is greater than the minimum detection light intensity, then any light intensity within the range from the maximum tolerated light intensity to the minimum detection light intensity will be used as the slit lamp detection light intensity.
9. A non-transitory computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements a method for determining the light intensity of a slit lamp detection light as described in any one of claims 1 to 8.
10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements a method for determining the intensity of slit lamp detection light as described in any one of claims 1 to 8.