Novel medical instrument equipment for vision detection and control method thereof

Abstract

The invention relates to the technical field of vision detection, in particular to novel medical equipment for vision detection and a control method thereof. Determining that the to-be-detected child is located at a designated position, and triggering a detection program to start according to the age of the to-be-detected child Displaying a three-color sphere based on preset parameters, controlling the sphere to move based on a vision value locking algorithm, determining eyeball following times, and obtaining a vision value; on the basis of an amblyopia qualitative detection algorithm, controlling the sphere to move to obtain retinal imaging response delay time and child blinking frequency; based on the vision value, the retinal imaging response delay time and the child blinking frequency, a detection result is obtained through a child amblyopia detection algorithm model. According to the method, a vision value locking algorithm, an amblyopia qualitative detection algorithm and a child amblyopia detection algorithm model are adopted, the improved E word table quantitative logic and the improved OKN qualitative logic are fused through algorithms, quantitative and qualitative synchronous detection of child amblyopia is achieved, the detection efficiency is 2.7 times that of a traditional method, and the detection accuracy rate reaches 95% or above.

Description

Technical Field

[0001] This invention relates to the field of vision testing technology, and in particular to a novel medical device for vision testing and its control method. Background Technology

[0002] Existing vision testing equipment is designed based on adults, generally using the E chart or standard vision lightbox; it requires two-way interaction between the tester and medical staff, and young children aged 12 months to 3 years have difficulty understanding instructions, resulting in a success rate of less than 30%; moreover, there is no dedicated testing logic for the pathological characteristics of amblyopia in children, such as delayed retinal imaging and abnormal eye tracking function, which can easily be confused with ordinary myopia. The current method for amblyopia detection, namely the optokinetic nystagmus (OKN) method, is relatively primitive and has low detection efficiency. It relies on manually moving a striped board and judging visual acuity by observing the nystagmus of the child's eyes. It has three major drawbacks: First, the speed or frequency of movement depends on the experience of medical staff, with a subjective error of ±15%; second, it can only qualitatively determine whether amblyopia is present, and cannot quantitatively output visual acuity values; third, a single test takes 5-8 minutes, which is difficult for children to maintain their attention. To address the aforementioned issues, there is an urgent need for a medical device and corresponding testing method that can be adapted to vision testing of young children, meeting the needs for objective, rapid, and quantitative amblyopia testing in young children. Summary of the Invention

[0003] In view of the above problems, this disclosure provides a novel medical device for vision testing and its control method to overcome or at least partially solve the above problems. The purpose is to solve the problems of long interaction time and high subjectivity in existing vision testing relying on the E chart; and to solve the problems of slow speed and relatively primitive technology in existing amblyopia testing OKN method.

[0004] The objective of this invention can be achieved through the following technical solutions: The present invention provides a novel medical device for vision testing and its control method. The present invention provides a novel medical device for vision testing, comprising a base, a positioning module at one end of the base, and a display module at the other end; the positioning module includes a window assembly mounted on a window frame connected to the base; the window assembly has a window in the middle for observing the display module; a slidable baffle is embedded in the window of the window assembly; a chin rest module is provided at the lower end of the window assembly, the chin rest module including a chin rest base fixed to the window frame; a chin rest that can move up and down is embedded in the chin rest base; the base is provided with an image acquisition module and a power switch; the image acquisition module is opposite to the window; a sound module is provided in the outer shell of the display module; the display module, image acquisition module, positioning module, and sound module are electrically connected to a control module.

[0005] Furthermore, the image acquisition module is installed in a groove on the surface of the base; the camera of the image acquisition module is opposite to the viewing window; the lower part of the chin support base is provided with a telescopic control button for fixing the chin support; the chin support module has a built-in pressure sensor.

[0006] A control method for a novel medical device for vision detection includes: Once the child to be tested is located in the designated area, the testing procedure is initiated based on the child's age. A three-color sphere is displayed based on preset parameters. The movement of the sphere is controlled based on a visual acuity locking algorithm to determine the number of times the eye follows the sphere and obtain the visual acuity value. Based on the qualitative detection algorithm for amblyopia, the movement of a ball is controlled to obtain the retinal imaging response delay time and the blink frequency of children. The detection results are obtained based on visual acuity, retinal imaging response delay time, and children's blinking frequency, using a children's amblyopia detection algorithm model.

[0007] Furthermore, determining that the child to be detected is located at the designated location includes: The pressure sensor of the positioning module acquires pressure signal data; the image acquisition module acquires the eye position data of the child to be detected; the control module determines that the pressure signal data and the eye position data of the child to be detected meet the preset detection conditions, and determines that the child to be detected is located at the designated position.

[0008] Furthermore, the preset detection conditions include: Preset pressure detection conditions and preset position detection conditions; The preset pressure detection condition is that the pressure signal data is greater than a preset pressure threshold and remains stable for more than a preset time. The preset detection condition is that the child's eyes are located at the window position of the window component.

[0009] Furthermore, the step of triggering the detection procedure based on the age of the child to be tested includes: The control module acquires the age of the child to be detected, loads preset parameters based on the child's age, and plays preset guiding sound effects corresponding to the child's age; the preset parameters are the initial sphere diameter corresponding to the child's age.

[0010] Furthermore, the step of displaying a three-color sphere based on preset parameters, controlling the sphere's movement based on a visual acuity locking algorithm, determining the number of times the eye follows the sphere, and obtaining the visual acuity value includes: Based on preset parameters, black, gray, and white spheres are displayed; the vision value locking algorithm includes: controlling the spheres to move along a preset direction at a preset speed, and collecting the child's eye movement trajectory in real time through an image acquisition module; Through image analysis, if a child's eye follows the movement of the ball three times in a row, the diameter of the ball is controlled to decrease to the minimum diameter according to a preset ratio; through image analysis, if a child's eye does not follow the movement of the ball twice in a row, the visual acuity value corresponding to the diameter of the ball at that time is obtained.

[0011] Furthermore, the method based on the amblyopia qualitative detection algorithm, controlling the movement of the sphere to obtain the retinal imaging response delay time and the child's blink frequency, includes: The qualitative detection algorithm for amblyopia includes: controlling the sphere to move along a preset direction at a preset speed, and collecting the child's eye movement trajectory in real time through an image acquisition module; Image analysis is used to obtain the retinal imaging response delay time. If the child's eye response delay time to the sphere is greater than the delay threshold and the child's eye tracking accuracy is less than the tracking threshold, a preliminary judgment result is obtained. The frequency of children's blinking was obtained through image analysis.

[0012] Furthermore, the detection results obtained through the amblyopia detection algorithm model for children, based on visual acuity, retinal imaging response delay time, and children's blink frequency, include: The system integrates multi-dimensional data such as visual acuity, retinal imaging response delay time, and children's blink frequency as input, and outputs detection results through a children's amblyopia detection algorithm model. The detection results include quantitative visual acuity, amblyopia risk level, and recommended follow-up examination time.

[0013] Furthermore, the amblyopia detection algorithm model for children adopts a deep learning model, using visual acuity, retinal imaging response delay time, and children's blinking frequency as training data, and outputs detection results through the trained deep learning model.

[0014] The technical solution proposed in this application can bring the following beneficial effects: 1. This invention employs a visual acuity value locking algorithm, an amblyopia qualitative detection algorithm, and a children's amblyopia detection algorithm model. It integrates the improved E-chart quantitative logic and the improved OKN qualitative logic through algorithmic fusion to achieve simultaneous quantitative and qualitative detection of children's amblyopia.

[0015] 2. This invention utilizes a visual acuity locking algorithm and an amblyopia qualitative detection algorithm, along with dynamic stimulation technology using black, gray, and white three-color spheres and eye-tracking technology. This eliminates errors caused by differences in children's subjective cognition, achieving a detection efficiency 2.7 times that of traditional methods and an accuracy rate of over 95%. It is suitable for children aged 12 months to 14 years, especially for younger children aged 12 months to 3 years, providing an efficient tool and method for early amblyopia screening.

[0016] The above description is merely an overview of the technical solution disclosed herein. In order to better understand the technical means of this disclosure and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this disclosure more apparent and understandable, specific embodiments of this disclosure are described below. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this disclosure. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a schematic diagram of the structure of the novel vision testing medical device provided in the embodiments of this specification; Figure 2 This is a flowchart of the steps of the control method for the novel vision testing medical device provided in the embodiments of this specification; Figure 3 This is a schematic diagram of the structure of a novel vision testing medical device module provided in the embodiments of this specification.

[0018] The components include: 1. Display module; 2. Image acquisition module; 3. Power switch; 4. Base; 5. Sound module; 6. Window assembly; 7. Movable baffle; 8. Chin support module; 9. Telescopic control button; 10. Positioning module; and 11. Control module. Detailed Implementation

[0019] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. The technical solutions provided by various embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0020] Figure 1 This is a structural schematic diagram of a novel vision testing medical device provided in one or more embodiments of this specification.

[0021] This application provides a novel medical device for vision testing, including a base 4, with a positioning module at one end and a display module 1 at the other end; The positioning module includes a window component and a chin support module; The positioning module includes a viewing window component 6, which is mounted on a viewing window frame connected to the base 4; the viewing window frame is used to mount the viewing window component and to limit head movement; for example, the viewing window frame is a rectangular panel. The viewing window assembly 6 has a viewing window in the middle for observing the display module; the dynamic graphics displayed by the display module 1 can be seen through the viewing window; the viewing window assembly has an arc-shaped protrusion for fixing the eye area and providing a cushioning effect, and is made of soft sponge material.

[0022] The window assembly 6 has a sliding movable baffle 7 embedded in its window; the movable baffle is used to block undetected eyes, and its position can also be adjusted so that both eyes are not blocked.

[0023] The lower end of the viewing window assembly 6 is provided with a chin support module 8. The chin support module includes a chin support base fixed to the viewing window frame. The chin support base is embedded with a chin support that can move up and down. The chin support can move up and down to adjust the position of the child's head to be tested, so that the chin can be effectively fixed and supported. The position can be adjusted so that the child's eyes can be located in the viewing window position. For example, the chin rest is located in the central cavity of the chin rest base. The position of the chin rest is fixed by a telescopic control button, which can be a fastening screw. The chin rest is fixed by rotating and clamping it.

[0024] The base 4 is equipped with an image acquisition module 2 and a power switch 3; the image acquisition module 2 is opposite to the viewing window; the outer shell of the display module 1 is equipped with a sound module 5, which includes a speaker; the display module 1, the image acquisition module 2, the positioning module 10, and the sound module 5 are electrically connected to the control module 11 respectively.

[0025] The image acquisition module is installed in a groove on the surface of the base; the camera of the image acquisition module is opposite to the window; by adjusting the angle of the camera of the image acquisition module, the camera can completely capture the image of the window component position, and the camera can completely capture the image of the child's eye to be detected at the window position.

[0026] The chin rest base is equipped with a telescopic control button for fixing the chin rest; The chin support module has a built-in pressure sensor; when the child's chin is in the chin support, the built-in pressure sensor collects pressure signal data and transmits the pressure signal data to the control module.

[0027] like Figure 2 As shown in the figure, this application provides a control method for a novel medical device for vision testing, specifically including: S101. Determine that the child to be tested is located in the designated location, and trigger the start of the testing procedure based on the child's age; S102. Display a three-color sphere based on preset parameters, control the movement of the sphere based on a visual acuity locking algorithm, determine the number of times the eye follows the sphere, and obtain the visual acuity value. S103. Based on the amblyopia qualitative detection algorithm, control the movement of the ball to obtain the retinal imaging response delay time and the child's blinking frequency; S104. Based on visual acuity, retinal imaging response delay time, and children's blinking frequency, the detection results are obtained through a children's amblyopia detection algorithm model.

[0028] The step of determining that the child to be detected is located at a designated location includes: The pressure sensor of the positioning module acquires pressure signal data; the image acquisition module acquires the eye position data of the child to be detected; the control module determines that the pressure signal data and the eye position data of the child to be detected meet the preset detection conditions, and determines that the child to be detected is located at the designated position.

[0029] When the pressure signal data is within the preset threshold range and the duration reaches the set time, and the deviation between the eye position captured by the image acquisition module and the standard fixation point is less than the allowable error, the control module determines that the child to be tested is in the correct position and triggers the start of the detection program.

[0030] The preset detection conditions include: Preset pressure detection conditions and preset position detection conditions; The preset pressure detection condition is that the pressure signal data is greater than a preset pressure threshold and remains stable for more than a preset time. The preset detection condition is that the child's eyes are located at the window position of the window component.

[0031] A pressure sensor collects real-time pressure signal data generated by the child's chin against the chin rest. This data is used to determine whether the child's head has made stable contact with the device, initially confirming that their body is close to the device. The pressure sensor signal must continuously exceed a set threshold (example pressure threshold is 1.5 kg) and remain stable for more than a preset time (example preset time is 0.5 seconds) to rule out brief, unintentional touches by the child and confirm that the head is properly positioned and remains still. This is the initial positioning signal.

[0032] The image acquisition module captures video streams containing children's faces in real time, and accurately identifies and outputs the position data of the child's eyes through the built-in facial landmark detection (FaceLandmarkDetection) in the control module. The position data of the child's eyes is represented by the coordinates of the pupils in the image coordinate system.

[0033] Once the control module receives pressure signal data that meets the preset pressure detection conditions, it determines that the child to be detected is initially positioned. Then, the control module immediately calls the data from the image acquisition module for analysis. Through image analysis, it obtains the coordinates of both pupils and compares them with the pre-stored standard detection area in the device, ensuring that the position data of the child's eyes meets the following conditions: Horizontal alignment: The line connecting the coordinates of the pupils of both eyes is basically horizontal, and the difference in the Y coordinate is within the allowable range; Vertical position: The vertical coordinates of both pupils are located in the middle of the standard area; Relative distance: The pixel distance between the pupils of both eyes is within a reasonable range to ensure that the distance between the child and the lens is appropriate; By using the positional data of the child's eyes, it is ensured that the child's eyes are directly facing the eyepiece of the vision tester at an appropriate distance, and that there is no deviation in their line of sight.

[0034] The control module determines that the child to be detected is in the designated position only when both the pressure preset detection condition and the position preset detection condition are met simultaneously.

[0035] The step of triggering the detection procedure based on the age of the child to be tested includes: The control module acquires the age of the child to be detected, loads preset parameters based on the child's age, and plays preset guiding sound effects corresponding to the child's age; the preset parameters are the initial sphere diameter corresponding to the child's age.

[0036] When the control module determines that the child to be detected is in the designated location, the control module automatically controls the display module to display the child's age selection interface. For example, the age group can be selected through the touch panel. The age groups include the first group: 12 months to 3 years, the second group: 3 to 5 years, the third group: 5 to 7 years, the fourth group: 7 to 14 years, and the fifth group: 14 years and above. Adults or children can select the corresponding age group via the touch panel, at which point the control module obtains the age of the child to be tested; Then, preset parameters are loaded according to age group. For example, the initial diameter of the sphere is 20mm for children under 3 years old and 10mm for children over 7 years old. Once the child to be tested is located at the designated position, the control module obtains the child's age. At this time, based on the child's age, the control module controls the sound module to emit a prompt tone, for example, the prompt tone is "Testing is about to begin"; then, the corresponding age group's guiding sound effect is played, for example, a baby's laughter is played for the 12-month group.

[0037] The process of displaying a three-color sphere based on preset parameters, controlling the sphere's movement based on a visual acuity locking algorithm, determining the number of times the eye follows the sphere, and obtaining the visual acuity value includes: Based on preset parameters, black, gray, and white spheres are displayed; the vision value locking algorithm includes: controlling the spheres to move along a preset direction at a preset speed, and collecting the child's eye movement trajectory in real time through an image acquisition module; Through image analysis, if a child's eye follows the movement of the ball three times in a row, the diameter of the ball is controlled to decrease to the minimum diameter according to a preset ratio; through image analysis, if a child's eye does not follow the movement of the ball twice in a row, the visual acuity value corresponding to the diameter of the ball at that time is obtained.

[0038] This step is the vision value locking stage, which is designed based on the improved E-table logic. The child's vision value is obtained by the child's reaction to the ball. Specifically, the following steps are included: Step 1: Visual acuity value locking initialization phase: After confirming that the child has been successfully located, the control module sends a command to the display module, which then generates a black, gray, and white sphere with an initial diameter at a preset starting position on the screen. For example, the black sphere has a contrast of 90% for young children, the gray sphere has a contrast of 60% for school-aged children, and the white sphere serves as a background reference.

[0039] Step 2: Trajectory Generation and Sphere Motion Control the sphere to move left and right in a preset direction at a preset speed; The control module drives the ball to move smoothly on the screen along the selected trajectory at a speed suitable for children to follow, with an example speed set to 5 cm / s.

[0040] Step 3: Real-time acquisition and analysis of eye movement trajectories: The infrared camera in the image acquisition module continuously captures images of the child's eyes at a high frame rate (such as 60fps and above).

[0041] Each frame of the image is processed in real time through image analysis. By using technologies such as pupil positioning and corneal reflection, the system accurately calculates and outputs the movement trajectory data of the child's eyeball at every moment, including the rotation angle or screen coordinates in the horizontal and vertical directions.

[0042] Step 4: Follow-up judgment: The real-time eye movement trajectory is compared with the ball's movement trajectory in a spatiotemporal synchronization; if the eye movement direction is consistent with the ball's movement direction, it is determined that the child's eye is following the ball's movement.

[0043] Since the movement of the eyeball relative to the movement of the sphere is delayed within a reasonable physiological response time, for example, less than 200 milliseconds.

[0044] A valid follow is defined as the sphere completing a complete preset path, such as moving from the left side of the screen to the right side, and the eye trajectory continuously meets the above criteria during this period.

[0045] Step 5: Shrinking Phase Once the control module determines that the child has successfully followed the sphere of the current diameter three times in a row, the control module will initiate the difficulty upgrade program. Proportional Decrease: The control module drives the display module according to a preset ratio to generate a smaller sphere. For example, the diameter of the sphere decreases by 5% per increment until it shrinks to a minimum diameter of 2mm.

[0046] Cyclic detection: Repeat steps two through five, with the sphere continuing to move in a new, smaller diameter, and ask the child to track it.

[0047] When a child fails to follow a sphere of a certain size three times consecutively, for example, if the child loses the follow twice during the attempt, the system records the diameter of the sphere at the time of the last successful pass as the final score, and records the visual acuity value corresponding to the diameter of the sphere at this time. For example, a diameter of 5mm corresponds to a visual acuity of 0.4.

[0048] Image analysis of eye movement trajectories can be performed using facial landmark detection (FAR) and deep learning methods.

[0049] The method of controlling the movement of a sphere based on the amblyopia qualitative detection algorithm to obtain the retinal imaging response delay time and the child's blink frequency includes: The qualitative detection algorithm for amblyopia includes: controlling the sphere to move along a preset direction at a preset speed, and collecting the child's eye movement trajectory in real time through an image acquisition module; Image analysis is used to obtain the retinal imaging response delay time. If the child's eye response delay time to the sphere is greater than the delay threshold and the child's eye tracking accuracy is less than the tracking threshold, a preliminary judgment result is obtained. Image analysis is also used to obtain the child's blinking frequency.

[0050] The delay threshold is 0.5 seconds, and the retinal imaging response time of a normal child should be less than or equal to 0.3 seconds. The tracking threshold is set at 70%; if the child's eyeballs respond to a randomly moving ball with a delay of more than 0.5 seconds and the vertical movement tracking accuracy is less than 70%, it is preliminarily determined that the child has a tendency towards amblyopia.

[0051] This step is the qualitative detection stage for amblyopia, used for identification; Specifically, the following steps are included: Step 1: Initialization phase of qualitative detection for amblyopia: The control module sends a command to the display module, which generates a black, gray, and white sphere of initial diameter at a preset starting position on the screen. For example, the black sphere has a contrast ratio of 90% for young children; the gray sphere has a contrast ratio of 60% for school-aged children; and the white sphere serves as a background reference.

[0052] Step 2: Trajectory Generation and Sphere Motion The ball is controlled to move in a preset direction at a preset speed; including a first movement mode: vertical up and down movement, with a movement speed set to 3cm / s; and a second movement mode: random direction movement, with a trajectory of a sine curve, and a movement speed set to 2-6cm / s. Each mode lasts for 30 seconds.

[0053] Step 3: Real-time acquisition and analysis of eye movement trajectories: The infrared camera in the image acquisition module continuously captures images of the child's eyes at a high frame rate (such as 60fps and above).

[0054] By performing real-time processing on each frame of the image through image analysis, the time-series data of the ball's motion trajectory is precisely synchronized with the time-series data of the eye's motion trajectory.

[0055] Step 4: Calculation of retinal imaging response delay time: Identify the moment T1 when the sphere begins to move or changes direction, and then identify the moment T0 when the eye begins to follow the sphere. Calculate the average delay for all valid attempts: the delay time is the average of the difference between the mean T0 and T1.

[0056] Step 5: Calculation of eye-tracking accuracy: Calculate the pixel distance between the eye's fixation point and the center of the sphere at each time point to obtain the position error; count the percentage of time points in the entire tracking process where the position error is less than the allowable range (such as 25% of the sphere's diameter), which is the tracking accuracy.

[0057] Step 6: Calculate blink frequency: Through image analysis, the number of blinks per unit time is counted by identifying the eyelid closure state during the detection process, with the unit time set to per minute.

[0058] The detection results, obtained through a children's amblyopia detection algorithm model based on visual acuity, retinal imaging response delay time, and children's blink frequency, include: The system integrates multi-dimensional data such as visual acuity, retinal imaging response delay time, and children's blink frequency as input, and outputs detection results through a children's amblyopia detection algorithm model. The detection results include quantitative visual acuity, amblyopia risk level, and recommended follow-up examination time.

[0059] The amblyopia detection algorithm model for children adopts a deep learning model, using visual acuity, retinal imaging response delay time, and children's blinking frequency as training data, and outputs detection results through the trained deep learning model.

[0060] In this embodiment, the deep learning model is trained using a convolutional neural network (CNN) to obtain a child amblyopia detection algorithm model, which includes a feature extraction layer, a feature fusion and splicing layer, a fully connected layer, and an output layer.

[0061] The control module calls the amblyopia detection algorithm model for children and inputs the following data: visual acuity value; accuracy of eye tracking and retinal imaging response delay time of the child; blinking frequency of the child during the detection process. The algorithm integrates multi-dimensional data and outputs three types of results: First result: quantitative visual acuity value, such as OD of 0.3 and OS of 0.5; Second result: amblyopia risk level, including no risk, mild, moderate and severe; Third result: recommended follow-up time, such as mild amblyopia is recommended to be followed up after 3 months. The results are displayed on the monitor module in the form of "cartoon charts and simplified text", such as green stars to indicate no risk and yellow triangles to indicate mild risk. At the same time, the auditory module plays result prompts, such as "The test is complete, you are great". It supports exporting test reports that include raw data curves, etc.

[0062] The novel vision testing medical device and its control method according to this embodiment were tested and verified as follows: 1. Experimental subjects and grouping Partnering Unit: A tertiary children's ophthalmology hospital; Grouping: The children were divided into 5 groups according to age, with 30 cases in each group, for a total of 150 cases. Among them, 50 children with known amblyopia (as positive control) and 100 healthy children (as negative control) were included. Inclusion criteria: 12 months to 14 years old, no history of eye surgery, and able to cooperate to complete the 3-minute test.

[0063] 2. Test methods The device of this invention performs the following tests: it is operated according to the above control method, and the test time, visual acuity value, and amblyopia determination result are recorded. Traditional testing methods include: E chart (ages 5 and up), graphic vision chart (ages 5 and under); manual OKN testing requires medical staff to hold a striped board and record the corresponding results. Comparison indicators: testing time, result accuracy rate, and child cooperation.

[0064] 3. Test Results: Regarding the average detection time for the indicators: the average detection time of the device of this invention is 2.5 minutes / person (±0.3 minutes); the average detection time of the traditional method is 6.8 minutes / person (±1.2 minutes). Regarding the concordance rate between the indicators and clinical diagnoses: the concordance rate between the device of this invention and clinical diagnoses was 95.3% (143 / 150 cases); the concordance rate between the traditional method and clinical diagnoses was 82.0% (123 / 150 cases). Regarding the child cooperation rate: the child cooperation rate of the device of this invention is 92.0% (138 / 150 cases completed the test); the child cooperation rate of the traditional method is 68.0% (102 / 150 cases completed the test). Regarding the accuracy of amblyopia classification: the amblyopia classification accuracy of the device of this invention is 93.6% (46 / 49 children with amblyopia); the accuracy of amblyopia classification using traditional methods is 75.5% (37 / 49 children with amblyopia). The device of this invention is significantly superior to traditional methods in terms of detection efficiency, result accuracy, and children's cooperation. It can also quantitatively output visual acuity values ​​and amblyopia levels, thus solving the pain points of existing technologies.

[0065] This embodiment can divide the novel vision testing medical device into functional modules according to the above method example. For example, each function can be assigned to a separate module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0066] By dividing the device into functional modules corresponding to each function, the novel vision testing medical device may include: a display module, an image acquisition module, a positioning module, a control module, etc. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0067] The novel vision testing medical device provided in this embodiment is used to execute the control method of the novel vision testing medical device described above, and therefore can achieve the same effect as the above implementation method.

[0068] When using integrated units, the novel vision testing medical device may include a processing module and a storage module. The processing module is used to control and manage the operation of the novel vision testing medical device. The storage module is used to support the execution of program code and data by the novel vision testing medical device.

[0069] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as disclosed in this application. The processor may also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0070] This embodiment also provides a computer-readable storage medium (including but not limited to disk storage, CD-ROM, optical storage, etc.) storing computer program code. When the computer program code is run on a computer, the computer executes the above-mentioned related method steps to realize the novel vision detection medical device and its control method provided in the above embodiment.

[0071] This embodiment also provides a computer program product. When the computer program product is run on a computer, it causes the computer to perform the aforementioned steps to realize the novel vision detection medical device and its control method provided in the above embodiment. The beneficial effects of the above embodiments can be found in the corresponding methods described above, and will not be repeated here.

[0072] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0073] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. In the description of this disclosure, it should be understood that if terms such as "upper," "lower," "front," "rear," "left," and "right" are used to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, they are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the indicated position or element must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this disclosure.

[0074] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0075] The above are merely embodiments of this disclosure and are not intended to limit the scope of this disclosure. Various modifications and variations can be made to this disclosure by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of the claims of this disclosure.

Claims

1. A new medical device for vision testing, comprising a base, characterized in that, The base is provided with a positioning module at one end and a display module at the other end; the positioning module comprises a window assembly which is installed on a window frame connected with the base; the window assembly is provided with a window in the middle for observing the display module; a movable shutter is embedded in the window of the window assembly; the lower end of the window assembly is provided with a chin support module, and the chin support module comprises a chin support base fixed on the window frame; the chin support base is embedded with a chin support which can move up and down; the base is provided with an image acquisition module and a power switch; the image acquisition module is opposite to the window; the shell of the display module is provided with a sound module; the display module, the image acquisition module, the positioning module and the sound module are respectively electrically connected with the control module.

2. A new medical device for vision testing according to claim 1, characterized in that, The image acquisition module is installed in the groove on the surface of the base; the camera of the image acquisition module is opposite to the window; the lower part of the chin support base is provided with a telescopic control button for fixing the chin support; the chin support module is built-in with a pressure sensor.

3. The control method of the novel visual detection medical device according to claim 1, wherein, determining that the child to be detected is located at a specified position, triggering a detection program to start according to the age of the child to be detected; displaying a three-color sphere based on preset parameters, locking an algorithm based on a visual value, controlling the movement of the sphere, determining the number of eye followings, and obtaining the visual value; controlling the movement of the sphere based on a weak vision qualitative detection algorithm, obtaining the retinal imaging response delay time and the blinking frequency of the child; obtaining the detection result through a child weak vision detection algorithm model based on the visual value, the retinal imaging response delay time and the blinking frequency of the child.

4. The control method of a new visual detection medical device apparatus according to claim 3, characterized in that, The determination that the child to be detected is located at a specified position comprises: The pressure sensor of the positioning module acquires pressure signal data; the image acquisition module acquires eye position data of the child to be detected; the control module judges whether the pressure signal data and the eye position data of the child to be detected meet preset detection conditions, and determines that the child to be detected is located at a specified position.

5. A new medical device for vision testing and its control method according to claim 4, characterized in that, The preset detection conditions comprise: a pressure preset detection condition and a position preset detection condition; The pressure preset detection condition is that the pressure signal data is greater than a preset pressure threshold and remains stable for more than a preset time; The position preset detection condition is that the eyes of the child to be detected are located at the window position of the window assembly.

6. A new medical device for vision detection and its control method according to claim 3, characterized in that, The triggering of the detection program to start according to the age of the child to be detected comprises: The control module acquires the age of the child to be detected, loads preset parameters based on the age of the child to be detected, and plays a preset guiding sound effect corresponding to the age of the child; the preset parameters are the initial sphere diameter corresponding to the age of the child.

7. A new medical device for vision detection and its control method according to claim 3, characterized in that, The display of a three-color sphere based on preset parameters, the locking of an algorithm based on a visual value, the control of the movement of the sphere, the determination of the number of eye followings, and the obtaining of the visual value comprise: displaying black, gray and white three-color spheres based on preset parameters; the visual value locking algorithm comprises: controlling the sphere to move along a preset direction at a preset moving speed, and acquiring the eye movement trajectory of the child in real time through the image acquisition module; If the child's eyeball follows the ball movement for three times in succession, the diameter of the ball is controlled to decrease to the minimum diameter according to the preset proportion; if the child's eyeball does not follow the ball movement for two times in succession, the visual acuity value corresponding to the diameter of the ball at this time is obtained through image analysis.

8. A new medical device for vision detection and its control method according to claim 3, characterized in that, The weak vision qualitative detection algorithm based on the ball movement, the retinal imaging response delay time and the child's blink frequency are obtained, and the weak vision qualitative detection algorithm based on the ball movement includes: The weak vision qualitative detection algorithm includes: controlling the ball to move along a preset direction at a preset moving speed, and collecting the child's eyeball movement trajectory in real time through the image acquisition module; The retinal imaging response delay time is obtained through image analysis, and if the response delay time of the child's eyeball to the ball is greater than the delay threshold value and the child's eyeball following accuracy is less than the following threshold value, a preliminary determination result is obtained; The child's blink frequency is obtained through image analysis.

9. A new visual acuity detection medical device and its control method according to claim 3, characterized in that, The detection result is obtained through the child weak vision detection algorithm model based on the visual acuity value, the retinal imaging response delay time and the child's blink frequency, and the detection result includes: After the visual acuity value, the retinal imaging response delay time and the child's blink frequency are fused in multiple dimensions, the fused data are taken as input, the detection result is output through the child weak vision detection algorithm model, and the detection result includes the quantitative visual acuity value, the weak vision risk level and the recommended review time.

10. A novel visual acuity detection medical device and its control method according to claim 9, characterized in that, The child weak vision detection algorithm model adopts a deep learning model, the visual acuity value, the retinal imaging response delay time and the child's blink frequency are taken as training data, and the detection result is output through the trained deep learning model.

Images