Amblyopia perceptual training data determination method and amblyopia perceptual training optotypes
By acquiring test data from the target group and healthy individuals of the same age, the weak areas of amblyopia patients can be accurately located. The E-shaped optotype is used to dynamically adjust training parameters, which solves the problem of lack of personalization and dynamism in amblyopia perception training and improves training effectiveness and efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING TONGREN HOSPITAL AFFILIATED TO CAPITAL MEDICAL UNIV
- Filing Date
- 2026-04-02
- Publication Date
- 2026-07-03
AI Technical Summary
Existing amblyopia perception training lacks personalized and dynamic adjustments, resulting in unsatisfactory training effects.
By acquiring test data from the target subjects and healthy subjects of the same age, initial and reference contrast sensitivity data are determined, weak areas are accurately located, and training parameters are dynamically adjusted based on the weak data. Training is performed using E-shaped visual targets.
It improves the targeting and efficiency of training, reduces ineffective training time, ensures the stability and repeatability of training results, and reduces training risks.
Smart Images
Figure CN121964061B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of rehabilitation training technology, specifically to a method for determining amblyopia perception training data and amblyopia perception training visual target. Background Technology
[0002] Amblyopia is a common visual developmental disorder with a high incidence rate among children. It is characterized by best-corrected visual acuity in one or both eyes being lower than the normal visual acuity for its age, without any organic lesions found during eye examination. If amblyopia is not treated promptly and effectively, it can not only affect the patient's visual function, leading to low vision and loss of stereoscopic vision, but also seriously impact their learning, daily life, and future career development.
[0003] Currently, there are many treatment methods for amblyopia in clinical practice, among which perceptual training is an important intervention. This involves improving the visual perception ability of amblyopic patients and enhancing their visual acuity through specific visual stimuli and training tasks. Common methods include setting parameters based on visual acuity chart results, where the size and sharpness of the target to be recognized during training are roughly determined based on the trainee's visual acuity test values; and manually adjusting the training content based on the doctor's clinical experience, where the doctor directly sets training parameters, such as contrast, based on their assessment of the patient's condition.
[0004] However, in practical applications, the effectiveness of perceptual training is often significantly affected by the rationality of training parameter adjustments. Because the causes, severity, and characteristics of visual function deficits vary among each amblyopia patient, using uniform or imprecise training parameters is unlikely to achieve ideal treatment results. Therefore, how to achieve personalized and dynamic adjustment of training parameters has become a key issue in improving the effectiveness of amblyopia perceptual training. Summary of the Invention
[0005] This invention provides a method for determining amblyopia perception training data and amblyopia perception training visual targets to solve the problem that amblyopia perception training in the prior art is relatively fixed and lacks targeted training.
[0006] In a first aspect, the present invention provides a method for determining amblyopia perception training data, the method comprising:
[0007] Obtain test data for the target object, which is obtained from the target object's basic visual perception test;
[0008] Based on the test data, determine the initial contrast sensitivity data of the target object;
[0009] Obtain reference contrast sensitivity data, which is obtained by performing amblyopia perception tests on healthy subjects of the same age as the target subject;
[0010] Based on the initial and reference contrast sensitivity data, the weak data of the target object are identified;
[0011] Based on the weak data, determine the training data for the target object.
[0012] This invention focuses on targeted training of weak areas, reducing ineffective training in normal areas, saving significant amounts of unnecessary training time, and improving the efficiency and specificity of amblyopia perception training. Furthermore, this embodiment employs standardized measurement and training procedures, ensuring the stability and repeatability of training results, facilitating its clinical application.
[0013] In one optional implementation, based on initial contrast sensitivity data and reference contrast sensitivity data, the weak data of the target object are determined, including:
[0014] Based on the reference contrast sensitivity data, the deviation of each spatial frequency in the initial contrast sensitivity data is determined;
[0015] Based on the deviation, the weak spatial frequency and the degree of weakness of the weak spatial frequency are determined;
[0016] Weak data includes weak spatial frequencies and the degree of weakness of weak spatial frequencies.
[0017] By calculating the deviation of the CS value of each user's spatial frequency point from the standard value of the same age group, we can accurately locate the weak spatial frequency points that are significantly lower and form a continuous weak interval. At the same time, the magnitude of the deviation value also directly quantifies the degree of weakness of visual ability at that frequency point, providing a clear target and priority basis for personalized visual training.
[0018] In one alternative implementation, the training data for the target object is determined based on weak data, including:
[0019] Step a1: Determine the initial spatial frequency from the weak spatial frequencies based on the degree of weakness;
[0020] Step a2: Determine the initial contrast based on the test data;
[0021] Step a3: Generate a target display image based on the initial spatial frequency and initial contrast.
[0022] Step a4: Obtain the observation results and response time after the target object observation target image is displayed;
[0023] Step a5: Determine the training score based on the observations and response time;
[0024] Step a6: Determine the contrast adjustment step size based on the training score;
[0025] Step a7: Based on the initial spatial frequency, contrast adjustment step size, and current contrast, generate the target display image for the next display, and repeat steps a4 to a6.
[0026] In this embodiment, the training parameters are dynamically updated based on the weak data, making the training more scientific and reasonable. This avoids undertraining or overtraining caused by fixed parameters and excessively long adjustment cycles, thus reducing training risks.
[0027] In one alternative implementation, if the observed results show consecutive errors for a first preset number of times, the initial spatial frequency is re-determined from the weak spatial frequencies based on the degree of weakness, and steps a2 to a7 are repeated. This enables dynamic training throughout the process, reducing the workload of medical staff.
[0028] In one alternative implementation, after redetermining the initial spatial frequency a second preset number of times, a third preset number of interfering visual target images are added. This prevents users from developing fixed response patterns, thereby improving training effectiveness.
[0029] In one alternative implementation, the method further includes:
[0030] Intermediate contrast sensitivity data are generated at preset training intervals;
[0031] Based on intermediate contrast sensitivity data and reference contrast sensitivity data, the intermediate contrast sensitivity values for each weak spatial frequency are determined;
[0032] If the sensitivity value is compared for the fourth consecutive preset number of times and the preset threshold is increased, weak data is regenerated, and training data for the target object is determined based on the regenerated weak data.
[0033] This implementation method can continuously update the contrast sensitivity curve during the process of continuous training and parameter adjustment, helping doctors to better understand the patient's current visual level and progress / regression, and providing doctors with a more accurate basis for formulating subsequent treatment plans.
[0034] In one alternative implementation, the main body of the target in the target display image adopts an E-shape; the size of the target body is determined by the following steps:
[0035] Determine the test distance between the target object and the image displayed on the target;
[0036] Determine the spatial frequency of the target object;
[0037] The size of the target body is determined based on the test distance and spatial frequency.
[0038] Compared to traditional optotypes, the sine E symbol in this implementation is easier for children with amblyopia to understand, and helps to obtain more objective examination and training parameters.
[0039] Secondly, the present invention provides a visual acuity training target for amblyopia, applicable to a method for determining visual acuity training data in accordance with the first aspect above or any corresponding embodiment thereof; the visual acuity training target adopts an E-shaped structure.
[0040] In one alternative implementation, the brightness distribution of the target display image for displaying amblyopia perception training targets conforms to a sinusoidal periodicity.
[0041] This invention employs an E-shaped visual training target for amblyopia. This target is formed by filtering the E-shaped structure with a sine operator, which retains the "spatial frequency tuning" characteristics of the sine grating, preserves the signal purity of the target as much as possible, and improves ease of use, making the target object easier to understand. This effectively enhances the visual sensitivity and recognition ability of the target object, providing a better training effect for amblyopia training.
[0042] Thirdly, the present invention provides a system for determining training data for amblyopia perception, the system comprising:
[0043] The test data acquisition module is used to acquire test data of the target object. The test data is the data obtained by the target object through a basic test of amblyopia perception.
[0044] The determination module is used to determine the initial contrast sensitivity data of the target object based on the test data;
[0045] The reference data acquisition module is used to acquire reference contrast sensitivity data, which is obtained by performing amblyopia perception tests on healthy subjects of the same age as the target subject.
[0046] The weak data identification module is used to identify the weak data of the target object based on the initial contrast sensitivity data and the reference contrast sensitivity data.
[0047] The training data determination module is used to determine the training data for the target object based on weak data.
[0048] Fourthly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the amblyopia perception training data determination method of the first aspect or any corresponding embodiment described above.
[0049] Fifthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the amblyopia perception training data determination method of the first aspect or any corresponding embodiment described above.
[0050] In a sixth aspect, the present invention provides a computer program product, including computer instructions for causing a computer to execute the method for determining amblyopia perception training data described in the first aspect or any corresponding embodiment thereof.
[0051] It should be noted that, since the amblyopia perception training data determination system, electronic device, computer-readable storage medium, and computer program product provided by this invention correspond to the aforementioned amblyopia perception training data determination method, the beneficial effects of the amblyopia perception training data determination system, electronic device, computer-readable storage medium, and computer program product are described in the above description of the corresponding beneficial effects of the amblyopia perception training data determination method, and will not be repeated here. Attached Figure Description
[0052] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0053] Figure 1 This is a schematic diagram of the first step in the method for determining amblyopia perception training data according to an embodiment of the present invention.
[0054] Figure 2 This is a schematic diagram of the contrast sensitivity curve and sampling probability according to an embodiment of the present invention;
[0055] Figure 3 This is a schematic diagram of a target according to an embodiment of the present invention;
[0056] Figure 4 This is a structural block diagram of a system for determining amblyopia perception training data according to an embodiment of the present invention;
[0057] Figure 5 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.
[0059] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.
[0060] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.
[0061] According to an embodiment of the present invention, a method for determining training data for amblyopia is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0062] This embodiment provides a method for determining amblyopia perception training data, which can be used on servers, terminals, mobile terminals, etc. Figure 1 This is a flowchart of a method for determining amblyopia perception training data according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:
[0063] Step S101: Obtain test data of the target object. The test data is the data obtained by the target object through a visual impairment perception basic test.
[0064] The target group in this embodiment can be amblyopic patients or healthy individuals; it can be children or adults, and no specific limitation is made here.
[0065] The test data is a basic test conducted before formal training on the target object to determine the minimum contrast that the target object can distinguish for different spatial frequency targets, that is, the contrast sensitivity (CS).
[0066] Specifically, the following steps can be used to conduct a basic visual perception test on the target subject:
[0067] Initialization phase: After inputting the basic information of the target object (name, gender, age, vision, etc.), the system automatically sets the initial parameters, including: spatial frequency 5 Hz / degree (medium frequency, the range most sensitive to the human eye), contrast 20%, Gaussian blur coefficient 2 pixels, etc.; the target is displayed in the center of the screen, and the background is a uniform grayscale (brightness 85 cd / m²).
[0068] Response identification phase: The target object responds to the direction of the object through the controller, such as the up, down, left, and right of the notch in the E shape. The system records the response result (correct / incorrect) and the response time (≤5 seconds, timeout is judged as an error).
[0069] Parameter adjustment phase: The parameters are adjusted using the "step method". If there are two consecutive correct responses, the contrast is reduced by 5% or the spatial frequency is increased by 2 cycles / degree. If there is one consecutive incorrect response, the contrast is increased by 8% or the spatial frequency is reduced by 1 cycle / degree. This process continues until the six key frequency points of 1, 3, 5, 10, 20 and 40 cycles / degree are covered. Each frequency point is tested three times. The minimum contrast that is correctly identified is taken as the threshold contrast for that spatial frequency.
[0070] Test data output stage: The system plots contrast sensitivity function (CSF) curves based on each spatial frequency threshold, referring to... Figure 2 As shown, the contrast sensitivity value for each spatial frequency is output, where the contrast sensitivity CS value = 1 / threshold contrast.
[0071] The CSF curve in this embodiment can be fitted using a composite fitting model of "Gaussian function + linear correction", as shown in the following formula: CS(f)=CS_max×exp(-(f-f0)² / (2σ_f²))+a×f+b;
[0072] Where: CS(f) is the contrast sensitivity corresponding to spatial frequency f, CS_max is the peak contrast sensitivity of the CSF curve, f0 is the peak frequency (corresponding to the spatial frequency most sensitive to the human eye), σ_f is the frequency bandwidth coefficient (reflecting the sharpness of the curve), and a and b are linear correction coefficients (compensating for fitting deviations at high / low frequency ends).
[0073] By fitting the test data using the least squares method, the fitting error can be controlled within ±5%, ensuring that the CSF curve can accurately reflect the contrast sensitivity characteristics of the target object across the entire frequency range.
[0074] Step S102: Based on the test data, determine the initial contrast sensitivity data of the target object.
[0075] As described above, during the basic testing phase, the system continuously adjusts parameters to perform basic testing on the target object and obtains the contrast sensitivity of the target object at each spatial frequency. In this embodiment, the obtained contrast sensitivity at each spatial frequency is used as the initial contrast sensitivity data of the target object.
[0076] Step S103: Obtain reference contrast sensitivity data. The reference contrast sensitivity data is obtained by performing amblyopia perception tests on healthy subjects of the same age as the target subject.
[0077] The basic testing process described above can be used to test healthy individuals of different ages to obtain a CS standard database. Specifically, CSF data from 1000 healthy individuals of different ages (5-30 years old) can be collected, with a spatial frequency range of 0.5-30 Hz / degree. In this embodiment, CSF data of individuals of the same age as the target subject can be queried from the CS standard database as reference data for comparison sensitivity.
[0078] Step S104: Based on the initial contrast sensitivity data and the reference contrast sensitivity data, determine the weak data of the target object.
[0079] In some optional implementations, step S104 above includes:
[0080] Step S1041: Based on the reference contrast sensitivity data, determine the deviation of each spatial frequency in the initial contrast sensitivity data.
[0081] For the same spatial frequency, the deviation is the difference between the initial contrast sensitivity data and the reference contrast sensitivity data. Specifically, the deviation of the target object at each spatial frequency point can be calculated using the following formula: D(f)=(μ(f)-CS_user(f)) / σ(f);
[0082] Where D(f) is the deviation of spatial frequency f, μ(f) is the average CS value of healthy people of the same age at spatial frequency f, CS_user(f) is the CS value of the target object at spatial frequency f, and σ(f) is the standard deviation of the CS value of healthy people of the same age at spatial frequency f.
[0083] Step S1042: Based on the deviation, determine the weak spatial frequency and the degree of weakness of the weak spatial frequency. The weak data includes the weak spatial frequency and the degree of weakness of the weak spatial frequency.
[0084] In some optional implementations, when the deviation is less than a preset threshold, the corresponding spatial frequency is determined as the weak spatial frequency; the corresponding degree of weakness is determined based on the deviation.
[0085] For example, when D(f) ≥ 1.645 (i.e., CS_user(f) is 10% lower than the mean of the same age group, corresponding to a one-sided 95% confidence interval in statistics), this spatial frequency point is determined to be a weak point, i.e., a weak spatial frequency; two or more consecutive weak points constitute a "weak frequency interval," which will be used as the training focus for the target object. Moreover, the higher the degree of weakness of a frequency point, the greater the degree of weakness, and the higher the probability value during training sampling.
[0086] By calculating the deviation of the CS value of each user's spatial frequency point from the standard value of the same age group, we can accurately locate the weak spatial frequency points that are significantly lower and form a continuous weak interval. At the same time, the magnitude of the deviation value also directly quantifies the degree of weakness of visual ability at that frequency point, providing a clear target and priority basis for personalized visual training.
[0087] Step S105: Based on the weak data, determine the training data for the target object.
[0088] In this embodiment, training data for the target object can be selected from the weak data, and training data for the target object can be selected again from the weak data based on the feedback from the target object, thereby achieving targeted training for the target object.
[0089] In this embodiment, targeted training is focused on weak areas, reducing ineffective training in normal areas, saving a significant amount of unnecessary training time, and improving the efficiency and specificity of amblyopia perception training. Furthermore, this embodiment employs standardized measurement and training procedures, ensuring the stability and repeatability of training results, facilitating clinical application.
[0090] In some alternative implementations, step S105 includes:
[0091] Step a1: Determine the initial spatial frequency from the weak spatial frequencies based on the degree of weakness.
[0092] Before determining the initial spatial frequencies, a "spatial frequency-training probability" mapping can be generated by normalizing the deviation D(f) of each spatial frequency point output by the weak interval identification algorithm, referring to... Figure 2 As shown, the horizontal axis represents spatial frequency, and the vertical axis represents training sampling probability. Frequency points with higher weakness correspond to higher probability values. The probability calculation uses normalization: P(f) = D(f) / ∑D(f), where ∑D(f) is the sum of the deviations of all spatial frequency points in the weak region.
[0093] The system performs random sampling based on the probability map. Spatial frequency points with higher probability values are more likely to be selected. Each sampling determines one target training spatial frequency, i.e., the initial spatial frequency.
[0094] Step a2: Determine the initial contrast based on the test data.
[0095] In this embodiment, the initial contrast can be set to 120% of the threshold contrast of the spatial frequency to ensure that the target object can be correctly identified.
[0096] In addition, contrast can be calculated using brightness. Specifically, the brightness modulation formula L(x,y)=L0+ΔL×sin(2πfx)×exp(-(x²+y²) / (2σ²)) is used to achieve precise contrast control. The Gaussian window exp(-(x²+y²) / (2σ²)) can be added or omitted depending on the actual situation. Here, L(x,y) is the brightness of any pixel on the target, L0 is the background brightness, ΔL is the brightness modulation amplitude, f is the spatial frequency, and σ is the Gaussian blur coefficient. The contrast is calculated as C=ΔL / L0, and supports adjustable steps of 0.1% within the contrast range of 0.5%-100%.
[0097] Step a3: Generate a target display image based on the initial spatial frequency and initial contrast.
[0098] Step a4: Obtain the observation results and response time after the target object observation target image is displayed.
[0099] Step a5: Determine the training score based on the observations and response time.
[0100] Step a6: Determine the contrast adjustment step size based on the training score.
[0101] Step a7: Based on the initial spatial frequency, contrast adjustment step size, and current contrast, generate the target display image for the next display, and repeat steps a4 to a6.
[0102] For the initial target frequency obtained from probabilistic map sampling, first set the initial adjustment step size k of gradient descent, for example, k = 5%, and the reaction time factor rt, where rt is in seconds. The reaction time factor rt is used to link with the initial adjustment step size coefficient k using a weighted combination method, specifically:
[0103] First, set the correctness score S_c (e.g., 10 points for correct and 0 points for incorrect) and the rt time score S_rt (e.g., calculated as "10-(rt / 5)×5", with a maximum of 10 points and 0 points when rt=5 seconds). Then, with a correctness weight of 60% and a rt time weight of 40%, calculate the comprehensive score S using the formula: S=0.6×S_c+0.4×S_rt.
[0104] Furthermore, the adjustment rule for k is as follows: if S≥9 points (fast and correct), k is increased by 1.2% (maximum k=8%) after 3 consecutive correct attempts, and reset to 5% for errors; if 7 points≤S<9 points (normal level), the original rule is maintained (k increases by 1% after 3 consecutive correct attempts, and resets to 5% for errors); if S<7 points (either slow or wrong), k is not increased after 3 consecutive correct attempts, and reset to 5% for errors, with the current contrast ratio used as the starting contrast ratio for the new round of training at that spatial frequency.
[0105] The patient's response time (the time from the presentation of the visual target to the response) is recorded simultaneously during the response process, which can effectively balance training efficiency and the accuracy of exploration of the limits of perception.
[0106] In this embodiment, the training parameters are dynamically updated based on the weak data, making the training more scientific and reasonable. This avoids undertraining or overtraining caused by fixed parameters and excessively long adjustment cycles, thus reducing training risks.
[0107] In some alternative implementations, if the observed results are continuously incorrect for a first preset number of times, the initial spatial frequency is re-determined from the weak spatial frequencies according to the degree of weakness, and steps a2 to a7 are re-executed.
[0108] After each training task is completed, if the recognition is correct, the contrast is adjusted according to the above adjustment rules; if the recognition is incorrect multiple times, that is, the contrast perception limit at the current frequency is reached, the training of the current spatial frequency is stopped, and the process returns to step a1 to resample the probability map and start the training of the next target spatial frequency, so as to realize the dynamic training of amblyopia perception and reduce the workload of medical staff.
[0109] In some alternative implementations, after the initial spatial frequency is redefined a second preset number of times, a third preset number of interference target display images are added.
[0110] For example, after every 5 spatial frequency sampling training sessions, a "frequency confusion test" (i.e., interfering with the target display image, randomly introducing non-weak frequency targets) is inserted to prevent users from forming fixed response patterns, thereby improving training effectiveness.
[0111] In some alternative implementations, the method further includes:
[0112] Step b1: Generate intermediate contrast sensitivity data at preset training intervals.
[0113] Step b2: Based on the intermediate contrast sensitivity data and the reference contrast sensitivity data, determine the intermediate contrast sensitivity value for each weak spatial frequency.
[0114] Step b3: After the intermediate contrast sensitivity value has been compared for the fourth consecutive preset number of times and the preset threshold has been increased, weak data is regenerated, and training data for the target object is determined based on the regenerated weak data.
[0115] For example, after every 30 minutes of training, a comparison report between the real-time CSF curve and the baseline CSF curve is output, indicating the magnitude of the difference in CS values for each spatial frequency. When the CS value of the weak spatial frequency range increases by ≥20% in two consecutive training sessions, the weak spatial frequency range is automatically updated and the training task is adjusted.
[0116] In this embodiment, the contrast sensitivity curve can be continuously updated during the training and parameter adjustment process, helping doctors to better understand the patient's current visual level and progress / regression, and providing doctors with a more accurate basis for formulating subsequent treatment plans.
[0117] In some alternative implementations, the main body of the target in the target display image adopts an E-shape; the size of the target body is determined by the following steps:
[0118] Step c1: Determine the test distance between the target object and the image displayed on the target.
[0119] Step c2: Determine the spatial frequency of the target object.
[0120] Step c3: Determine the size of the target body based on the test distance and spatial frequency.
[0121] In this embodiment, the main body of the target is an E-shaped target with equal side lengths, possessing directionality, specifically the direction of the E-shaped opening. (Refer to...) Figure 3 As shown.
[0122] In this embodiment, the target is generated by filtering the E-structure using a sine operator. It retains the "spatial frequency tuning" characteristic of the sine grating, preserves the signal purity of the target as much as possible, and improves usability, making the target object easier to understand.
[0123] Its spatial frequency can be calculated using the formula f=1 / (2θ), where f is the spatial frequency (Hz / degree) and θ is the target half-angle (degree). This allows for continuous adjustment of the spatial frequency across different spatial frequency ranges, covering the low, medium, and high frequency ranges. (Refer to...) Figure 3 As shown, taking a single visual target structure as an example, if it is cut off at the opening of the E-shape, the period can be obtained as 3.5.
[0124] Based on this, combined with the test distance L (unit: meters), the actual size of the target is further derived through the target half-angle θ: the target half-width s satisfies the geometric relationship with the test distance L and the half-angle θ: s=L×tan(θ×π / 180°); considering that θ is mostly a small angle (usually ≤5°) in visual testing, it can be approximated by s≈L×(θ×π / 180°); therefore, the target full width G is twice the half-width, that is, G=2s≈2L×(θ×π / 180°). Substituting θ=1 / (2f), the target full width can be directly determined through the spatial frequency f and the test distance L: G≈(L×π) / (180f), thereby achieving accurate matching of the actual size of the target under different spatial frequencies, ensuring that the target accurately transmits the target spatial frequency information through the corresponding half-angle θ at the set test distance.
[0125] Compared to traditional visual targets, such as Gabor gratings or sine gratings, the sine E-shaped symbol in this embodiment is easier for children with amblyopia to understand and helps to obtain more objective examination and training parameters.
[0126] Compared to the traditional binary detection mode of visual targets ("yes" or "no"), the sine E in this embodiment is a four-choice interactive mode ("up, down, left, right"), which is not easy for patients to guess correctly and can reduce the false negative rate. Based on this design, it can also help the curve to fit more accurately.
[0127] This embodiment also provides an amblyopia perception training visual target, which is applicable to the amblyopia perception training data determination method described in any of the above embodiments; the amblyopia perception training visual target adopts an E-shaped structure. For details, please refer to... Figure 3 As shown.
[0128] In some alternative implementations, the brightness distribution of the target display image for displaying amblyopia perception training targets conforms to a sinusoidal periodicity.
[0129] In this embodiment, an E-shaped visual perception training target is used. This target is formed by filtering the E-shaped structure with a sine operator, which retains the "spatial frequency tuning" characteristics of the sine grating, preserves the signal purity of the target as much as possible, and improves ease of use, making the target object easier to understand. This effectively enhances the visual sensitivity and recognition ability of the target object, providing a better training effect for amblyopia training.
[0130] This embodiment also provides a system for determining amblyopia perception training data, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.
[0131] This embodiment provides a system for determining training data for amblyopia perception, such as... Figure 4 As shown, it includes:
[0132] The test data acquisition module 401 is used to acquire the test data of the target object. The test data is the data obtained by the target object in the basic test of amblyopia perception.
[0133] Module 402 is used to determine the initial contrast sensitivity data of the target object based on the test data;
[0134] The reference data acquisition module 403 is used to acquire reference contrast sensitivity data, which is obtained by performing amblyopia perception tests on healthy subjects of the same age as the target subject.
[0135] The weak data determination module 404 is used to determine the weak data of the target object based on the initial comparison sensitivity data and the reference comparison sensitivity data.
[0136] The training data determination module 405 is used to determine the training data for the target object based on weak data.
[0137] In some alternative implementations, the weak data determination module 404 includes features specifically for:
[0138] Based on the reference contrast sensitivity data, the deviation of each spatial frequency in the initial contrast sensitivity data is determined;
[0139] Based on the deviation, the weak spatial frequency and the degree of weakness of the weak spatial frequency are determined;
[0140] Weak data includes weak spatial frequencies and the degree of weakness of weak spatial frequencies.
[0141] In some alternative implementations, the training data determination module 405 is specifically used for:
[0142] Step a1: Determine the initial spatial frequency from the weak spatial frequencies based on the degree of weakness;
[0143] Step a2: Determine the initial contrast based on the test data;
[0144] Step a3: Generate a target display image based on the initial spatial frequency and initial contrast.
[0145] Step a4: Obtain the observation results and response time after the target object observation target image is displayed;
[0146] Step a5: Determine the training score based on the observations and response time;
[0147] Step a6: Determine the contrast adjustment step size based on the training score;
[0148] Step a7: Based on the initial spatial frequency, contrast adjustment step size, and current contrast, generate the target display image for the next display, and repeat steps a4 to a6.
[0149] If the observation results are continuously incorrect for the first preset number of times, the initial spatial frequency is re-determined from the weak spatial frequencies according to the degree of weakness, and steps a2 to a7 are repeated.
[0150] After redetermining the initial spatial frequency a second preset number of times, an interference target display image is added a third preset number of times.
[0151] In some alternative implementations, the system further includes:
[0152] The update module is used to generate intermediate contrast sensitivity data every preset training time; based on the intermediate contrast sensitivity data and the reference contrast sensitivity data, the intermediate contrast sensitivity value of each weak spatial frequency is determined; when the intermediate contrast sensitivity value is increased for the fourth consecutive preset number of times and the preset threshold is increased, the weak data is regenerated, and the training data of the target object is determined based on the regenerated weak data.
[0153] The target generation module is used to determine the test distance between the target object and the target display image; determine the spatial frequency of the target object; and determine the size of the target body based on the test distance and spatial frequency.
[0154] The amblyopia perception training data determination system provided in this embodiment of the invention can execute the amblyopia perception training data determination method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.
[0155] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.
[0156] The following is a detailed reference. Figure 5The diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from memory 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device. The processor 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.
[0157] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.
[0158] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a memory 508, or installed from a ROM 502. When the computer program is executed by the processor 501, it performs the functions defined in the amblyopia perception training data determination method of the embodiments of the present invention.
[0159] Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.
[0160] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the amblyopia perception training data determination method shown in the above embodiments is implemented.
[0161] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.
[0162] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A method for determining training data for amblyopia perception, characterized in that, The method includes: Acquire test data of the target object, wherein the test data is the data obtained by the target object through a basic test of amblyopia perception. Based on the test data, the initial contrast sensitivity data of the target object is determined; Obtain reference contrast sensitivity data, which is obtained by performing amblyopia perception tests on healthy subjects of the same age as the target subject; Based on the initial contrast sensitivity data and the reference contrast sensitivity data, the weak data of the target object are determined; wherein, based on the reference contrast sensitivity data, the deviation of each spatial frequency in the initial contrast sensitivity data is determined; based on the deviation, the weak spatial frequency and the degree of weakness of the weak spatial frequency are determined; the weak data includes the weak spatial frequency and the degree of weakness of the weak spatial frequency. Based on the aforementioned weak data, training data for the target object is determined; wherein, the training data includes: Step a1: Determine the initial spatial frequency from the weak spatial frequencies based on the degree of weakness; Step a2: Determine the initial contrast based on the test data; Step a3: Based on the initial spatial frequency and the initial contrast, a target display image is generated; the target body in the target display image adopts an E-shaped structure, which is obtained by filtering the E-shaped structure with a sine operator, thus preserving the spatial frequency tuning characteristics of the sine grating. Step a4: Obtain the observation results and response time fed back by the target object after observing the target display image; Step a5: Determine the training score based on the observation results and the response time; Step a6: Based on the training score, determine the contrast adjustment step size; Step a7: Based on the initial spatial frequency, the contrast adjustment step size, and the current contrast, generate the target display image for the next display, and re-execute steps a4 to a6.
2. The method according to claim 1, characterized in that, If the observation results are continuously incorrect for a first preset number of times, the initial spatial frequency is re-determined from the weak spatial frequencies according to the degree of weakness, and steps a2 to a7 are re-executed.
3. The method according to claim 2, characterized in that, After the initial spatial frequency is redefined a second preset number of times, an interference target display image is added a third preset number of times.
4. The method according to claim 1, characterized in that, The method further includes: Intermediate contrast sensitivity data are generated at preset training intervals; Based on the intermediate contrast sensitivity data and the reference contrast sensitivity data, the intermediate contrast sensitivity value of each of the weak spatial frequencies is determined; If the intermediate contrast sensitivity value is exceeded for the fourth consecutive preset number of times and the preset threshold is increased, the weak data is regenerated, and the training data of the target object is determined based on the regenerated weak data.
5. The method according to any one of claims 1 to 4, characterized in that, The dimensions of the main body of the target are determined through the following steps: Determine the test distance between the target object and the target display image; Determine the spatial frequency of the target object; The size of the target body is determined based on the test distance and the spatial frequency.
6. A visual target for amblyopia perception training, characterized in that, The method for determining amblyopia perception training data is applicable to any one of claims 1 to 5; the amblyopia perception training visual targets adopt an E-shaped structure.
7. The visual target for amblyopia perception training according to claim 6, characterized in that, The brightness distribution of the visual target display image for the amblyopia perception training targets conforms to a sinusoidal periodicity.
8. A system for determining training data for amblyopia perception, characterized in that, The system includes: The test data acquisition module is used to acquire test data of the target object, wherein the test data is the data obtained by the target object in a basic test of amblyopia perception. The determination module is used to determine the initial contrast sensitivity data of the target object based on the test data; The reference data acquisition module is used to acquire reference contrast sensitivity data, which is obtained by performing amblyopia perception tests on healthy subjects of the same age as the target object. A weak data determination module is used to determine the weak data of the target object based on the initial contrast sensitivity data and the reference contrast sensitivity data; wherein, it includes: determining the deviation of each spatial frequency in the initial contrast sensitivity data based on the reference contrast sensitivity data; determining the weak spatial frequency and the degree of weakness of the weak spatial frequency based on the deviation; the weak data includes the weak spatial frequency and the degree of weakness of the weak spatial frequency; A training data determination module is used to determine the training data for the target object based on the weak data; wherein, it includes: Step a1: Determine the initial spatial frequency from the weak spatial frequencies based on the degree of weakness; Step a2: Determine the initial contrast based on the test data; Step a3: Based on the initial spatial frequency and the initial contrast, a target display image is generated; the target body in the target display image adopts an E-shaped structure, which is obtained by filtering the E-shaped structure with a sine operator, thus preserving the spatial frequency tuning characteristics of the sine grating. Step a4: Obtain the observation results and response time fed back by the target object after observing the target display image; Step a5: Determine the training score based on the observation results and the response time; Step a6: Based on the training score, determine the contrast adjustment step size; Step a7: Based on the initial spatial frequency, the contrast adjustment step size, and the current contrast, generate the target display image for the next display, and re-execute steps a4 to a6.
9. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the method for determining amblyopia perception training data as described in any one of claims 1 to 5.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method for determining amblyopia perception training data as described in any one of claims 1 to 5.