Goldmann intraocular pressure examination method and equipment based on artificial intelligence

Abstract

The present invention relates to the field of artificial intelligence technology, and in particular to a Goldmann intraocular pressure examination method and device based on artificial intelligence. The method comprises: in the process of observing an eye under examination with a low-power eyepiece of a slit lamp microscope, obtaining a fluorescent image of two fluorescent semi-rings in a low-power eyepiece collected in real time by a camera; by rotating a measuring drum wheel of a Goldmann tonometer to increase the pressure applied to the eye under examination, adjusting the fluorescent semi-ring features of the two fluorescent semi-rings, and identifying the fluorescent semi-ring features in the fluorescent image in real time based on a pre-trained deep learning model; when it is identified that the fluorescent semi-ring features meet feature requirements, reading the intraocular pressure value displayed by an electronic sensor knob; recording the intraocular pressure value corresponding to the fluorescent image and the knob value, and displaying it through a display screen; the present invention improves the accuracy and efficiency of intraocular pressure examination through a pre-trained deep learning model, and realizes real-time fluorescent semi-ring display and recording.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based Goldmann intraocular pressure testing method and device. Background Art

[0002] Goldmann intraocular pressure test is a commonly used ophthalmic diagnosis and treatment technique that measures the pressure inside the eyeball to assess the patient's eye health. However, the traditional Goldmann test method has some disadvantages. First, this method relies on the doctor's naked eye observation and manual operation, and is therefore easily affected by the doctor's personal experience and skill level. Secondly, when measuring, the doctor needs to observe the changes in the fluorescent semi-ring in real time and manually adjust the knob according to his own judgment to achieve the correct flattening degree. This subjectivity may lead to differences in measurement results between different doctors. Summary of the invention

[0003] The purpose of the present invention is to provide a Goldmann intraocular pressure examination method and equipment based on artificial intelligence, aiming to assist Goldmann intraocular pressure examination based on artificial intelligence, realize real-time fluorescent semi-ring display and recording, and improve the accuracy and efficiency of intraocular pressure examination.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] In a first aspect, an embodiment of the present invention provides a Goldmann intraocular pressure examination method based on artificial intelligence, wherein the method is applied to a Goldmann intraocular pressure examination system, wherein the Goldmann intraocular pressure examination system comprises: a slit lamp microscope, a Goldmann tonometer, an electronic sensor knob and a display screen, wherein the Goldmann tonometer comprises a measuring drum wheel, and the slit lamp microscope comprises a low-power eyepiece and a camera;

[0006] The method comprises the following steps:

[0007] During observation of the inspected eye through a low-power eyepiece of a slit lamp microscope, obtaining a fluorescent image of two fluorescent semi-rings in the low-power eyepiece collected in real time by a camera;

[0008] By rotating the measuring drum of the Goldmann tonometer to increase the pressure applied to the inspected eye, the fluorescent semi-ring features of the two fluorescent semi-rings are adjusted, and the fluorescent semi-ring features in the fluorescent image are recognized in real time based on a pre-trained deep learning model;

[0009] When it is identified that the fluorescent semi-ring feature meets the feature requirements, reading the intraocular pressure value displayed by the electronic sensor knob; wherein the feature requirements include that the two fluorescent semi-rings are completely symmetrical, the width reaches the set width value, and the inner diameters are tangent;

[0010] The fluorescent image and the intraocular pressure value corresponding to the knob value are recorded and displayed on a display screen.

[0011] Optionally, the slit lamp microscope further comprises a joystick, and before acquiring the fluorescent images of the two fluorescent semi-rings in the low-power eyepiece collected in real time by the camera, the method further comprises:

[0012] By adjusting the joystick of the slit lamp microscope, the two fluorescent half rings displayed on the display screen of the slit lamp microscope are located in the center of the field of view, and the two fluorescent half rings are symmetrical left to right and up to down, and have uniform width.

[0013] Optionally, the Goldmann intraocular pressure examination system further includes a sound prompt module, and the method further includes:

[0014] If it is determined that the intraocular pressure value exceeds a specific range, a corresponding sound prompt is issued through the sound prompt module.

[0015] Optionally, the identifying the fluorescent semi-ring feature in the fluorescent image based on a pre-trained deep learning model includes:

[0016] After preprocessing the fluorescence image, extracting the fluorescence semi-ring feature from the preprocessed fluorescence image;

[0017] The fluorescent semi-ring feature is input into a pre-trained deep learning model, the fluorescent semi-ring feature is identified, and the corresponding intraocular pressure value is read.

[0018] Optionally, the trained deep learning model is obtained by:

[0019] Preprocessing the fluorescence image, wherein the preprocessing includes denoising and contrast enhancement;

[0020] The convolutional neural network is used to extract the fluorescence semi-ring features from the preprocessed fluorescence images;

[0021] marking the fluorescent semi-ring features in the fluorescent image to obtain a marked fluorescent image;

[0022] Using the labeled fluorescence images and the corresponding intraocular pressure values ​​as training samples, and forming a data set with a plurality of the training samples;

[0023] A deep learning model is established, and the deep learning model is iteratively trained using the data set until the loss value of the deep learning model is lower than a set loss threshold or the number of iterative training reaches a set number threshold, thereby obtaining a trained deep learning model.

[0024] In a second aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0025] at least one processor;

[0026] at least one memory for storing at least one program;

[0027] When the at least one program is executed by the at least one processor, the at least one processor implements any one of the methods described above.

[0028] The beneficial effects of the present invention are as follows: the present invention discloses a Goldmann intraocular pressure examination method and device based on artificial intelligence, which improves the limitations of traditional methods and significantly improves the measurement accuracy and diagnostic consistency. The technology eliminates the errors caused by the doctor's subjective judgment by automatically analyzing the changes in the fluorescent semi-ring, ensuring the objectivity and repeatability of the measurement results. This not only improves the standardization level of diagnosis, but also optimizes the patient experience, making the examination process faster and smoother. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0030] Figure 1 Schematic diagram of a process of Goldmann intraocular pressure testing method based on artificial intelligence in an embodiment of the present invention;

[0031] Figure 2 Schematic diagram of the structure of the Goldmann intraocular pressure testing system in an embodiment of the present invention;

[0032] Figure 3 A schematic diagram of collecting a fluorescence image in an embodiment of the present invention;

[0033] Figure 4 is a schematic diagram of a fluorescent half ring in an embodiment of the present invention;

[0034] Figure 5 1 is a structural block diagram of an electronic device in an embodiment of the present invention.

[0035] Reference numerals: 100, camera; 200, Goldmann tonometer; 300, electronic sensor knob; 400, fluorescent image; 500, intraocular pressure value; DETAILED DESCRIPTION

[0036] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other without conflict.

[0037] See also Figures 1 to 4 The present invention provides a Goldmann intraocular pressure examination method based on artificial intelligence, the method is applied to a Goldmann intraocular pressure examination system, the Goldmann intraocular pressure examination system comprises: a slit lamp microscope, a Goldmann tonometer 200, an electronic sensor knob 300 and a display screen, the Goldmann tonometer 200 comprises a measuring drum wheel, the slit lamp microscope comprises a low-power eyepiece, a joystick and a camera 100;

[0038] The method comprises the following steps:

[0039] S100, in the process of observing the inspected eye through a low-power eyepiece of a slit lamp microscope, obtaining a fluorescent image 400 acquired in real time by the camera 100 of two fluorescent semi-rings in the low-power eyepiece;

[0040] Specifically, the sitting posture and slit lamp microscope are adjusted, and the examination begins; the low-power eyepiece of the slit lamp microscope is used to observe the inspected eye, and two yellow-green fluorescent semi-rings can be seen. The joystick of the slit lamp microscope is adjusted to make the two fluorescent semi-rings located in the center of the field of view, and the two fluorescent semi-rings are symmetrical left and right, up and down, and uniform in width; at the same time, the camera 100 captures the fluorescent image 400 of the fluorescent semi-ring in real time, and transmits the fluorescent image 400 to the data processing unit of the host.

[0041] In the related art, the slit lamp microscope is an important instrument that is indispensable for ophthalmic examination. The slit lamp microscope consists of an illumination system and a binocular microscope. It can not only observe superficial lesions very clearly, but also adjust the focus and the width of the light source to make an "optical section" so that lesions in deep tissues can also be clearly seen. The slit lamp microscope includes a joystick.

[0042] S200, rotating the measuring drum of the Goldmann tonometer 200 to increase the pressure applied to the examined eye, adjusting the fluorescent semi-ring features of the two fluorescent semi-rings, and recognizing the fluorescent semi-ring features in the fluorescent image 400 in real time based on a pre-trained deep learning model;

[0043] Specifically, the measuring drum of the Goldmann tonometer 200 is slowly rotated to increase the pressure applied to the eye under examination until the two fluorescent semi-rings are completely symmetrical, the width is about 1 / 10 (0.3 mm) of the diameter of the arc, and the inner diameters are tangent; in the embodiment provided by the present invention, in addition to the eyepiece of the slit lamp microscope, the doctor can also observe the changes of the fluorescent semi-rings in real time through the display screen. At the same time, the camera 100 captures the position of the fluorescent semi-rings in the eyepiece in real time and transmits the data to the data processing unit. After receiving the data, the data processing unit can automatically record the relevant data and read the knob value when the fluorescent semi-rings are inscribed.

[0044] In addition to real-time analysis and feedback, the embodiment provided by the present invention can also automatically record the fluorescent image 400 and analysis results of each examination, and generate a detailed examination report, providing convenience for doctors.

[0045] S300, when it is identified that the fluorescent semi-ring feature meets the feature requirements, reading the intraocular pressure value 500 displayed by the electronic sensor knob 300; wherein the feature requirements include that the two fluorescent semi-rings are completely symmetrical, the width reaches a set width value, and the inner diameters are tangent;

[0046] S400, recording the fluorescent image 400 and the intraocular pressure value 500 corresponding to the knob value, and displaying them on a display screen.

[0047] Specifically, the data processing unit extracts characteristic information of the fluorescent semi-ring, automatically records relevant data, and reads the knob value, that is, the intraocular pressure value, when the fluorescent semi-ring is inscribed, and then obtains the corresponding analysis result based on the intraocular pressure value; by building a pre-trained deep learning model into the data processing unit, accurate recognition and processing of the fluorescent image 400 can be achieved.

[0048] In this embodiment, the camera 100 is used to capture the position of the fluorescent semi-ring and transmit the collected fluorescent image 400 to a data processing unit (such as a computer host); the electronic sensor knob 300 is used to control the changes of the fluorescent semi-ring and transmit the data to the data processing unit in real time; the display screen displays the changes of the fluorescent semi-ring in real time; the data processing unit is responsible for receiving and processing the fluorescent image 400 from the camera 100, and performing intelligent analysis and judgment through a deep learning model; the sound prompt module issues a corresponding sound prompt based on the analysis results of the electronic device.

[0049] After receiving the fluorescence image 400, the data processing unit can automatically record relevant data and read the knob value of the electronic sensor knob 300 when the fluorescence semi-ring is inscribed. The data processing unit can extract key features from the pre-processed fluorescence image 400 by using a pre-trained deep learning model. Figure 2 and Figure 3As shown, the applanation pressure is increased by rotating the Goldmann tonometer 200 measuring drum wheel until the two fluorescent semi-rings are symmetrical and complete, the width is about 1 / 10 (0.3 mm) of the arc diameter, and the inner diameters are tangent, and the knob value is automatically read. The fluorescent image 400 and the intraocular pressure value 500 corresponding to the knob value are displayed on the display screen, so that the doctor can view the results intuitively.

[0050] In the embodiment provided by the present invention, the automation, intelligence and convenient operation of Goldmann intraocular pressure examination are realized through the pre-trained deep learning model, and the changes of the fluorescent semi-ring can be accurately identified to provide reliable intraocular pressure measurement results.

[0051] In some embodiments, the slit lamp microscope further comprises a joystick, and before acquiring the fluorescent image 400 acquired in real time by the camera 100 from the two fluorescent semi-rings in the low-power eyepiece, the method further comprises:

[0052] By adjusting the joystick of the slit lamp microscope, the two fluorescent half rings displayed on the display screen of the slit lamp microscope are located in the center of the field of view, and the two fluorescent half rings are symmetrical left to right and up to down, and have uniform width.

[0053] In some embodiments, the Goldmann intraocular pressure examination system further includes a sound prompt module, and the method further includes:

[0054] If it is determined that the intraocular pressure value exceeds a specific range, a corresponding sound prompt is issued through the sound prompt module.

[0055] Specifically, the sound prompt module issues a corresponding sound prompt based on the analysis results of the data processing unit. When the state of the fluorescent semi-ring changes and the intraocular pressure value exceeds a specific range, the sound prompt module will issue a prompt sound to help the doctor pay attention in time and make corresponding operations and adjustments.

[0056] In some embodiments, the identifying the fluorescent semi-ring feature in the fluorescent image 400 based on a pre-trained deep learning model includes:

[0057] After preprocessing the fluorescence image 400, a fluorescence semi-ring feature is extracted from the preprocessed fluorescence image 400;

[0058] The fluorescent semi-ring feature is input into a pre-trained deep learning model, the fluorescent semi-ring feature is identified, and the corresponding intraocular pressure value is read.

[0059] In some embodiments, the trained deep learning model is obtained by:

[0060] Preprocessing the fluorescence image 400, wherein the preprocessing includes denoising and contrast enhancement;

[0061] A convolutional neural network is used to extract the fluorescence semi-ring features from the pre-processed fluorescence image 400;

[0062] Annotating the fluorescent semi-ring feature in the fluorescent image 400 to obtain the annotated fluorescent image 400;

[0063] Using the labeled fluorescence image 400 and the corresponding intraocular pressure value as training samples, and forming a data set with a plurality of the training samples;

[0064] A deep learning model is established, and the deep learning model is iteratively trained using the data set until the loss value of the deep learning model is lower than a set loss threshold or the number of iterative training reaches a set number threshold, thereby obtaining a trained deep learning model.

[0065] The trained deep learning model can automatically identify the fluorescent semi-ring feature and trigger the data processing unit to read the intraocular pressure value corresponding to the knob value.

[0066] Below is a detailed description of the pre-trained deep learning model:

[0067] Image preprocessing: First, the received fluorescence image 400 is preprocessed, including operations such as denoising and contrast enhancement, so as to improve the image quality and provide a basis for subsequent feature extraction and recognition.

[0068] Feature extraction: Using the convolutional neural network (CNN) in deep learning, key features (fluorescence semi-ring features) are automatically identified and extracted from the pre-processed fluorescence image 400.

[0069] Real-time analysis and feedback: The deep learning model in the data processing unit can automatically identify qualified fluorescent rings and automatically read the intraocular pressure value at the same time. At the same time, the algorithm will also evaluate the prediction results and calculation results. When an abnormality or exceeding the preset range is found, the sound prompt module will be triggered to sound an alarm or display corresponding prompt information to alert the doctor.

[0070] In some embodiments, the method further comprises:

[0071] After the measurement of the examined eye is completed, the joystick of the slit lamp microscope is adjusted to withdraw the pressure measuring head from the examined eye, and one drop of antibacterial eye drops is instilled into the examined eye.

[0072] In the process of detecting the width of the fluorescent ring, the embodiment provided by the present invention further includes:

[0073] 1. Fluorescence ring width detection;

[0074] Real-time detection: During real-time analysis of fluorescent images, the system's built-in image processing algorithm can accurately detect the width of the fluorescent ring and automatically compare it with a preset ideal width range (such as 1 / 10 of the arc diameter, or 0.3mm).

[0075] Result feedback: Once the system detects that the width of the fluorescent ring exceeds the preset range, it will immediately trigger the error prompt mechanism to provide instant feedback to the doctor.

[0076] 2. Correction tips;

[0077] 2.1. Visual cues: In a prominent position on the display screen, the system not only displays fluorescent images and real-time rotation direction indicators, but also adds the following visual elements:

[0078] 2.1.1 Width indicator bar: A vertical bar graph that displays the current width value of the fluorescence ring in real time. The width indicator bar has a center mark (green area) that indicates the ideal width range (such as 0.3mm±0.02mm). When the width of the fluorescence ring exceeds this range, the corresponding part of the indicator bar (too thin or too thick) will be highlighted in red, accompanied by a flashing effect to attract the doctor's attention.

[0079] 2.1.2. Digital display area: The specific value of the current fluorescence ring width (accurate to one decimal place) is displayed next to or below the indicator bar for the doctor to read directly.

[0080] 2.1.3. Error icons and text: For different types of error situations, the system displays the corresponding error icon (such as an exclamation mark, arrow, etc.) and a brief text description in a corner of the screen, such as "increase pressure", "reduce pressure", "adjust the slit lamp position", etc., to quickly prompt the doctor to take action.

[0081] 2.2. Voice prompts: Combined with advanced speech synthesis technology, the system can issue clear and accurate voice prompts, as follows:

[0082] 2.2.1. The fluorescence ring is too thin: "Note that the current width of the fluorescence ring is too thin, which may lead to inaccurate measurement. It is recommended to increase the pressure of the Goldmann tonometer appropriately after leaving the cornea and re-contact the cornea for observation."

[0083] 2.2.2. The fluorescence ring is too thick: "Note that the current width of the fluorescence ring is too thick, which may be due to excessive tears or other reasons. Please try to reduce the pressure and check whether the measured eye needs to be wiped dry to re-measure."

[0084] 2.2.3. Different sizes of fluorescent rings: "Inconsistent sizes of fluorescent rings have been detected. Please adjust the position of the slit lamp and move it up and down in the direction of the larger half ring to try to balance the size of the two half rings."

[0085] 2.2.4. The fluorescent ring disappears: "Warning, a fluorescent ring has disappeared. Please immediately move the slit lamp to the left or right to the disappeared side to redisplay the disappeared half ring."

[0086] 2.2.5. High intraocular pressure: "Warning, even when the pressure is increased to the maximum, the two semicircles still fail to intersect, which indicates that the intraocular pressure may be extremely high (>80mmHg). Please stop measuring immediately and consider using a gravity balance bar or other advanced equipment for further evaluation."

[0087] Through such refinement of visual and voice prompts, the system can more comprehensively assist doctors in quickly identifying and correcting errors during the Goldmann intraocular pressure measurement process, thereby improving the accuracy and efficiency of the measurement.

[0088] 3. Automatic adjustment suggestions;

[0089] 3.1. Intelligent Recommendation: The system uses machine learning algorithms to combine the current fluorescence ring width, the doctor's previous adjustment operations, and historical data to intelligently recommend the next adjustment direction and approximate adjustment amount. These recommendations are designed to help doctors achieve the ideal fluorescence ring width more quickly.

[0090] 3.2. Interactive adjustment: After receiving the system's recommendation, the doctor can adjust the pressure through the fine-tuning button or slider. At the same time, the system will continuously monitor the changes in the width of the fluorescent ring and give new feedback or suggestions based on the actual situation, forming a closed-loop correction process.

[0091] Compared with the prior art solutions, the present invention has the following advantages:

[0092] Improve measurement accuracy: By applying a deep learning model based on AI intelligent assistance technology, the technology can automatically and objectively analyze the dynamic changes of the fluorescent semi-ring on the cornea. This transformation greatly reduces the errors caused by human factors, ensures that each measurement can achieve high consistency and accuracy, and provides more reliable data support for the early diagnosis of ophthalmic diseases.

[0093] Enhanced diagnostic consistency: Since the impact of differences in doctors' personal experience on the measurement results is eliminated, different doctors can obtain almost consistent measurement results when using the AI-based Goldmann intraocular pressure examination system, thereby improving the standardization level of diagnosis.

[0094] Optimize patient experience: The pre-trained deep learning model can quickly process and analyze data, making the examination process faster and smoother. It shortens the examination time, reduces the psychological burden on patients, and improves the overall medical experience.

[0095] and Figure 1 Corresponding to the method, refer to Figure 5 , an embodiment of the present invention provides an electronic device, including:

[0096] at least one processor;

[0097] at least one memory for storing at least one program;

[0098] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0099] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0100] In addition, an embodiment of the present invention further discloses a computer program product or a computer program, which is stored in a computer-readable storage medium. A processor of a computer device can read the computer program from a computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the above method. Similarly, the contents of the above method embodiment are all applicable to the storage medium embodiment, and the functions specifically implemented by the storage medium embodiment are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method embodiment.

[0101] It will be appreciated by those skilled in the art that all or some of the methods disclosed above and the system may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0102] The above is a specific description of the preferred implementation of the present disclosure, but the present disclosure is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions without violating the spirit of the present disclosure. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present disclosure.

Claims

1. A Goldmann intraocular pressure examination method based on artificial intelligence, characterized in that: The method is applied to a Goldmann intraocular pressure examination system, which comprises: a slit lamp microscope, a Goldmann intraocular pressure meter, an electronic sensor knob and a display screen, wherein the Goldmann intraocular pressure meter comprises a measuring drum wheel, and the slit lamp microscope comprises a low-power eyepiece and a camera; The method comprises the following steps: During observation of the inspected eye through a low-power eyepiece of a slit lamp microscope, obtaining a fluorescent image of two fluorescent semi-rings in the low-power eyepiece collected in real time by a camera; By rotating the measuring drum of the Goldmann tonometer to increase the pressure applied to the inspected eye, the fluorescent semi-ring features of the two fluorescent semi-rings are adjusted, and the fluorescent semi-ring features in the fluorescent image are recognized in real time based on a pre-trained deep learning model; When it is identified that the fluorescent semi-ring feature meets the feature requirements, reading the intraocular pressure value displayed by the electronic sensor knob; wherein the feature requirements include that the two fluorescent semi-rings are completely symmetrical, the width reaches the set width value, and the inner diameters are tangent; Recording the fluorescent image and the intraocular pressure value corresponding to the knob value, and displaying them on a display screen; The identifying of the fluorescent semi-ring feature in the fluorescent image based on the pre-trained deep learning model includes: After preprocessing the fluorescence image, extracting the fluorescence semi-ring feature from the preprocessed fluorescence image; The fluorescent semi-ring feature is input into a pre-trained deep learning model, the fluorescent semi-ring feature is identified, and the corresponding intraocular pressure value is read.

2. The method according to claim 1, characterized in that The slit lamp microscope further includes a joystick. Before the acquisition camera collects the fluorescent images of the two fluorescent semi-rings in the low-power eyepiece in real time, the method further includes: By adjusting the joystick of the slit lamp microscope, the two fluorescent half rings displayed on the display screen of the slit lamp microscope are located in the center of the field of view, and the two fluorescent half rings are symmetrical left to right and up to down, and have uniform width.

3. The method according to claim 1, characterized in that The Goldmann intraocular pressure testing system further includes a sound prompt module, and the method further includes: If it is determined that the intraocular pressure value exceeds a specific range, a corresponding sound prompt is issued through the sound prompt module.

4. The method according to claim 1, characterized in that: The trained deep learning model is obtained in the following way: Preprocessing the fluorescence image, wherein the preprocessing includes denoising and contrast enhancement; The convolutional neural network is used to extract the fluorescence semi-ring features from the preprocessed fluorescence images; marking the fluorescent semi-ring features in the fluorescent image to obtain a marked fluorescent image; Using the labeled fluorescence images and the corresponding intraocular pressure values ​​as training samples, and forming a data set with a plurality of the training samples; A deep learning model is established, and the deep learning model is iteratively trained using the data set until the loss value of the deep learning model is lower than a set loss threshold or the number of iterative training reaches a set number threshold, thereby obtaining a trained deep learning model.

5. An electronic device, characterized in that: The electronic device comprises: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 4.

Images