Glaucoma detection and classification system and head-mounted device

Abstract

This disclosure relates to a glaucoma detection and classification system, comprising: a measurement module for measuring the geometric topology data of the eyeball of the same subject under different environmental conditions at different time points within a set time period; and a classification module for classifying the eye condition of the subject based on the geometric topology data of the eyeball measured by the measurement module under the different environmental conditions. This disclosure also relates to a head-mounted device.

Description

Technical Field

[0001] This disclosure relates to eye health screening and disease screening, particularly to the detection and classification of glaucoma. Background Technology

[0002] Glaucoma is an eye disease that causes vision loss due to damage to the optic nerve. Damage to the optic nerve is generally believed to be caused by excessively high intraocular pressure (also known as high pressure within the eye), leading to overloading of the optic nerve.

[0003] A common method for detecting glaucoma involves visual field testing, which uses a slit lamp to observe the inner eyeball and obtain tomographic scans of the eye to comprehensively assess the condition of the optic nerve. This method is generally considered to accurately assess the condition of the optic nerve; however, these tests are not prospective and generally cannot judge or predict the progression of the disease in the tested individual, or even the risk of healthy individuals developing glaucoma.

[0004] Another common method for glaucoma detection is to measure intraocular pressure (IOP) using a tonometer. IOP is a commonly used diagnostic indicator for assessing the risk of glaucoma and the effectiveness of treatment, and it can provide further predictive data. If the measured IOP is high (>21 mmHg), the risk of optic nerve damage is higher, requiring medical follow-up. However, high IOP is not a necessary characteristic of having glaucoma, or a higher probability of developing glaucoma. In Europe and America, 10% to 48% of open-angle glaucoma patients have normal-tension glaucoma, while in China, this proportion is even higher than 50%.

[0005] It is evident that neither routine ophthalmological observation nor intraocular pressure measurement can comprehensively reflect the condition of the eyes, making it difficult to effectively assess disease progression or the chance of developing glaucoma. Summary of the Invention

[0006] To address at least the aforementioned problems, a glaucoma detection and classification system and a head-mounted device for eye detection are provided.

[0007] According to one aspect of this disclosure, a system for detecting and classifying glaucoma is provided, the system comprising:

[0008] The measurement module is used to measure the geometric topological data of the same subject's eyeball under different environmental conditions at different time points within a set time period; and

[0009] The classification module is used to classify the eye state of the subject based on the geometric topological data of the eyeball measured by the measurement module under different environmental conditions.

[0010] According to another aspect of this disclosure, a head-mounted device for eye detection is provided, the head-mounted device being wearable on the head of a subject and forming, together with the subject's body surface, a closed cavity surrounding the subject's eyes, wherein...

[0011] The head-mounted device is equipped with a catheter connector, which can regulate the pressure in the sealed cavity by controlling the flow of gas.

[0012] The head-mounted device has an observation channel at a position corresponding to the eyes of the subject, allowing the operator to detect the subject's eyeballs through the observation channel.

[0013] The glaucoma detection and classification system disclosed herein utilizes the topological changes in the eyeball caused by the adaptive response of related biological tissues to different environmental conditions and loading. By measuring these geometrical topological changes, the system can accurately classify the eye condition of the subject, thereby accurately assessing the health status of the subject's eyes, the risk of developing glaucoma, or the progression of glaucoma. Furthermore, the detection and classification system disclosed herein is non-invasive and can be safely implemented.

[0014] Furthermore, the head-mounted device provided in this disclosure can provide precise external loading to the subject's eyeball without hindering the acquisition of geometric topological data of the subject's eyeball, thereby facilitating the accurate assessment of the compliance of eye-related biological tissues and the accurate classification of the subject's eye condition. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of a glaucoma detection and classification system according to an embodiment of the present disclosure;

[0016] Figure 2 This is a schematic diagram of another glaucoma detection and classification system according to an embodiment of the present disclosure;

[0017] Figure 3 This is a flowchart of the process for glaucoma detection and classification based on Example 1 of this disclosure;

[0018] Figure 4 This is a flowchart of the process of classifying the eye condition of a subject based on the obtained eye geometric topology data according to Example 1 of this disclosure;

[0019] Figure 5 This is a schematic diagram of the function of the normalized astigmatic axis angle value according to Example 1 of this disclosure; and

[0020] Figure 6This is a flowchart of the process for glaucoma detection and classification based on Example 2 of this disclosure. Detailed Implementation

[0021] To enable those skilled in the art to better understand the technical solutions of this disclosure, the exemplary embodiments provided by this disclosure will be described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the features in the various embodiments, embodiments, and examples of this disclosure can be arbitrarily combined with each other.

[0022] The inventors noted that intraocular pressure (IOP) is a dynamically changing bioindicator with fluctuations and rhythms. Both routine ophthalmological observations and IOP measurements only reflect the eye's state at a single instant during the test, and therefore may not comprehensively reflect the eye's condition. Furthermore, high IOP is not the only cause of optic nerve damage. The optic nerve's biological tissues are also affected by the stress and strain caused by eye movements. The biotissue strength that optic nerve-related biological tissues can withstand is generally related to tissue compliance. Tissue compliance varies from person to person and may decrease with age or certain diseases. If the optic nerve-related biological tissues have low compliance, they will experience higher stress when subjected to increased IOP or eye movements, thus increasing the chance of damage. In addition, the mechanical characteristics of biological tissues are generally non-linear, and their response is time-dependent.

[0023] In view of this, embodiments of this disclosure provide a system for the detection and classification of glaucoma. For example... Figure 1 As shown, the detection and classification system includes: a measurement module 20, used to measure the geometric topology data of the same subject's eyeball under different environmental conditions at different time points within a set time period; and a classification module 30, used to classify the subject's eye condition based on the geometric topology data of the eyeball measured by the measurement module 20 under the different environmental conditions.

[0024] The detection and classification system of this disclosure utilizes the topological changes in the eyeball caused by the adaptive response of related biological tissues to different environmental conditions and loading. By measuring these geometrical topological changes, the system can accurately classify the eye condition of the subject, thereby accurately assessing the health status of the subject's eyes, the risk of developing glaucoma, or the progression of glaucoma. Furthermore, the detection and classification system of this disclosure is non-invasive and can be safely implemented.

[0025] In some implementations, the different environmental conditions include different pressures, such that the subject's eyeballs are subjected to different degrees of loading at least twice in multiple measurements.

[0026] In some embodiments, the different environmental conditions may include at least two of the following environmental conditions: i) ambient atmospheric pressure; ii) pressure below ambient atmospheric pressure; and iii) pressure above ambient atmospheric pressure.

[0027] In some implementations, the different environmental states include those that progress over time: ambient atmospheric pressure, pressure below ambient atmospheric pressure, and ambient atmospheric pressure.

[0028] In some implementations, the different environmental states include those that progress over time: ambient atmospheric pressure, pressure above ambient atmospheric pressure, and ambient atmospheric pressure.

[0029] In some implementations, the different environmental states may include normal environmental states (ambient atmospheric pressure) and loaded environmental states induced by the subject. Specifically, the subject may simultaneously press both nostrils together to hold their breath using their fingers or an assistive device, and then blow their nose to increase the intranasal pressure. The increased intranasal pressure will load the eyes to a certain extent, thereby changing the topology of the eyeball.

[0030] In some implementations, the different environmental conditions may also include the same or different preset temperatures.

[0031] In some implementations, such as Figure 2 As shown, the glaucoma detection and classification system according to an embodiment of the present disclosure further includes an environment setting module 10, which is used to provide the different environmental states for the eyeball of the subject being tested.

[0032] In some implementations, the measurement module 20 performs multiple measurements on the eyeball for each environmental condition, and the classification module 30 calculates the average value of the geometric topological data of the eyeball measured in each environmental condition.

[0033] In some implementations, considering the efficiency and accuracy of the measurement, the measurement module 20 measures the eyeball at intervals of 15 to 30 seconds. Of course, other time intervals are also possible.

[0034] In some implementations, the geometric topological data of the eyeball includes corneal topography of the eyeball.

[0035] In some implementations, the geometric topological data of the eyeball includes corneal angiography.

[0036] In some implementations, the geometric topological data of the eyeball includes tomographic scan data of the eyeball.

[0037] In some embodiments, the measurement module 20 includes anterior corneal coherence tomography, corneal angiography, or corneal topography.

[0038] In some embodiments, the measurement module 20 is also used to acquire parameters of the geometric topology data of the eyeball.

[0039] In some implementations, the parameters of the eye's geometric topology data are the astigmatic axis angles extracted from the geometric topology data.

[0040] In some implementations, the parameters of the geometric topology data of the eyeball are the normalized astigmatic axis angle.

[0041] In some embodiments, the classification module 30 is also used to formulate a function of how the parameters of the eye's geometric topology data change with environmental conditions.

[0042] In some implementations, the function is a time function or a pressure function.

[0043] In some implementations, the classification module 30 is also used to calculate the derivative of the function.

[0044] In some implementations, the classification module 30 is also used to calculate the slope of the derivative.

[0045] In some embodiments, the classification module 30 is also used to classify the eye condition of the subject based on the magnitude of the slope.

[0046] In some implementations, the classification module 30 obtains the rate of change of parameters of the geometric topology data of the eyeball as a function of environmental conditions by fitting the data, and classifies the eye condition of the subject based on the rate of change.

[0047] In some embodiments, the results of classifying the eye condition of the subject are used to indicate the risk of the subject developing glaucoma or the progression of the subject's glaucoma condition.

[0048] Embodiments of the present invention also provide a head-mounted device for eyeball detection. This head-mounted device can be worn on the head of a subject and, together with the subject's body surface (e.g., the surface of the eye socket, face, and neck), forms a closed cavity surrounding the subject's eyes. The head-mounted device includes a conduit connector that can adjust the pressure within the closed cavity by controlling the flow of gas. Furthermore, the head-mounted device has an observation channel at a position corresponding to the subject's eyes, allowing an operator to detect the subject's eyeballs through the observation channel.

[0049] In some embodiments, the head-mounted device can be used as the environment setting module 10 in the above-described detection and classification system.

[0050] Using the aforementioned head-mounted device, precise external loading can be provided to the subject's eyeballs without hindering the acquisition of geometric topological data of the subject's eyeballs. This facilitates accurate assessment of the compliance of eye-related biological tissues and accurate classification of the subject's eye condition.

[0051] In some embodiments, the conduit connector is connected to a gas conduit, through which gas is introduced into or out of the closed cavity.

[0052] In some implementations, the pressure in the enclosed cavity is set by controlling the flow rate of the gas.

[0053] In some embodiments, the pressure in the closed cavity is set by controlling the composition of the gas introduced into the closed cavity.

[0054] In some embodiments, the gas is selected from air, water vapor, and nitrogen.

[0055] In some embodiments, the gas conduit or the conduit connector is connected to an air pump.

[0056] In some embodiments, the head-mounted device is also provided with a pressure sensor that senses the pressure in the enclosed cavity.

[0057] In some embodiments, the observation channel is an opening fitted with a transparent material.

[0058] In some embodiments, the opening is connected to an observation device via a connecting device.

[0059] In some embodiments, the observation device is selected from anterior corneal coherence tomography (PCT) instruments, corneal angiography instruments, and corneal topography instruments.

[0060] Below, in conjunction with Figures 3 to 6 The specific examples shown illustrate the process of detecting and classifying glaucoma using a detection and classification system according to embodiments of the present disclosure.

[0061] Example 1

[0062] In this example, the subject of the test implements the loading of the environment state (loading on the eyeball) himself.

[0063] like Figure 3 As shown, the process of detecting and classifying glaucoma according to this example includes the following steps 110 to 180.

[0064] Step 110: Arrange for the person being tested to rest for about 5 minutes or more before the test to allow them to calm down.

[0065] Step 120: Under conditions without any external loading (i.e., at ambient atmospheric pressure), the geometric topological data of the subject's eyeball is measured using an anterior corneal coherence tomography instrument or corneal angiography instrument, which is an example of measurement module 20, as a raw reference.

[0066] It is worth mentioning that measurements can be repeated without external loading to ensure that the subject is not in a state of excessive fluctuation.

[0067] Step 130: Based on the results of the previous two or more measurements, confirm whether the condition of the subject's eyes has not fluctuated significantly. If the confirmation result is negative, the process returns to step 110; otherwise, the process continues to step 140.

[0068] Step 140: Instruct the subject to press both nostrils tightly with their fingers or an auxiliary device to hold their breath, while simultaneously blowing their nose to increase nasal pressure. This increase in nasal pressure will apply a certain degree of load to the subject's eyes.

[0069] Step 150: While the subject is holding their breath and blowing their nose, the geometric topological data of the eyeball when the eye is loaded is measured using the anterior corneal coherence tomography instrument or corneal angiography instrument.

[0070] Step 160: After the first measurement is completed, have the subject relax and rest for 15 to 30 seconds.

[0071] Specifically, the repeated loading measurement and rest cycle can be performed two or more times (i.e., steps 140-160 are repeated at least once).

[0072] Step 170: Under unloaded conditions, repeat the measurement of the geometric topology data of the subject's eyeball two or more times.

[0073] Step 180: Based on the obtained geometric topology data of the eyeball, the classification module 30 classifies the eye state of the subject according to predetermined conditions.

[0074] like Figure 4 As shown, step 180 above may include the following sub-steps 181 to 188:

[0075] Step 181: Extract corneal topological data from the measurement results of the measurement module (anterior corneal coherence tomography instrument or corneal angiography instrument).

[0076] Step 182: Extract the astigmatic axis angle value from the corneal topology data.

[0077] Step 183: Calculate the average astigmatic axis angle under loaded and unloaded conditions.

[0078] Step 184: Use the above average value as the base for normalizing the astigmatic axis angle value.

[0079] Step 185: Establish a normalized astigmatic axis angle as a function of loaded and unloaded conditions.

[0080] Step 186: Calculate the derivative of the above function.

[0081] Step 187: Calculate or analyze the slope of the above function based on the above derivative.

[0082] Step 188: Classify the eye condition according to the magnitude of the slope.

[0083] In an actual test, the results obtained for subject 1 and subject 2 are listed in Table 1 and Table 2 below, respectively.

[0084] Time (s) load Astigmatism axis angle (deg) Normalized astigmatism axis angle 0 0 86 1.0000 37 1 85 0.98837 63 1 78 0.90698 88 1 71 0.82558 117 0 87 1.0116 138 0 86 1.0000

[0085] Table 1, Data of Subject 1

[0086]

[0087]

[0088] Table 2, Data of Subject 2

[0089] Since the reaction time is generally lower during the first loading, the results obtained from the first loading can be ignored (i.e., the data from the 37th second of Detector 1 and the data from the 32nd second of Detector 2).

[0090] The average values ​​of the results without loading were calculated, resulting in an average astigmatism axis angle of 86 degrees for Subject 1 and 82 degrees for Subject 2 without loading. These average values ​​were used as the normalized base for each subject. Then, a function for the normalized astigmatism axis angle with loading as the independent variable was established, as shown in [reference needed]. Figure 5 .

[0091] from Figure 5 It is evident that the slope of Subject 1 is significantly lower than that of Subject 2. Therefore, it can be concluded that Subject 1 has a lower risk of glaucoma, while Subject 2 has a higher risk of glaucoma.

[0092] Example 2

[0093] In this example, the head-mounted device according to the invention provides the test subject with different environmental states (no loading state and at least one loading state).

[0094] like Figure 6 As shown, the process of detecting and classifying glaucoma according to this example includes the following steps 210 to 290.

[0095] Step 210: Have the subject wear the head-mounted device.

[0096] Step 220: Arrange for the person being tested to rest for about 5 minutes or more before the test to allow them to calm down.

[0097] Step 230: Under conditions without any external loading (zero gauge pressure), use an anterior corneal coherence tomography instrument or corneal angiography instrument, which serves as an example of a measurement module, to measure the geometric topological data of the subject's eyeball as a raw reference.

[0098] It is worth mentioning that measurements can be repeated without external loading to ensure that the subject is not in a state of excessive fluctuation.

[0099] Step 240: Based on the results of the previous two or more measurements, confirm whether the condition of the subject's eyes has not fluctuated significantly. If the confirmation result is negative, the process returns to step 220; otherwise, the process continues to step 250.

[0100] Step 250: Operate the inner cavity of the head-mounted device to the set negative pressure (negative gauge pressure) to subject the subject's eyes to a certain degree of loading.

[0101] Step 260: Measure the geometric topological data of the eyeball of the subject when the eye is loaded using the aforementioned anterior corneal coherence tomography instrument or corneal angiography instrument.

[0102] Advantageously, the measurement step is repeated two or more times, with an interval of 15 to 30 seconds between the two measurements.

[0103] Step 270: Have the subject relax for 15 to 30 seconds, while adjusting the inner cavity of the head-mounted device back to the unloaded condition (zero gauge pressure).

[0104] Step 280: Under unloaded conditions, repeat the measurement of the geometric topology data of the subject's eyeball two or more times.

[0105] Step 290: Based on the obtained geometric topological data of the eyeball, the classification module 30 classifies the eye state of the subject according to predetermined conditions.

[0106] It should be noted that the classification process in step 290 is similar to steps 181 to 188 in the previous example, and will not be repeated here.

[0107] Furthermore, in step 250 of the above example, the internal cavity of the head-mounted device can also be modulated with a positive gauge pressure.

[0108] Furthermore, geometric topological data can be measured under conditions of one or more negative gauge pressures, one or more positive gauge pressures, and zero gauge pressure. In this case, a normalized function of the astigmatic axis angle relative to the gauge pressure can be established, and the derivative / slope of this function can be calculated using algorithms such as fitting.

[0109] Those skilled in the art will understand that the above embodiments, implementation methods, and examples are merely illustrative, and this disclosure is not limited thereto. Various modifications and improvements can be made by those skilled in the art without departing from the spirit and substance of this disclosure, and these modifications and improvements are also considered to be within the scope of protection of this disclosure.

[0110] Those skilled in the art will understand that at least some of the modules disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. In hardware implementations, the division between functional modules mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media 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 technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, 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 known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0111] Furthermore, while specific terms are used in this disclosure, they are used only and should be interpreted in a general descriptive sense, and are not intended to be limiting. In some embodiments, it will be apparent to those skilled in the art that, unless otherwise expressly indicated, features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments.

Claims

1. A system for detection and classification of glaucoma, the system comprising: The detection and classification system comprises: a measurement module for measuring geometric topological data of the eyeball of the same subject under different environmental conditions at different time points within a set time period; and a classification module for classifying the eye condition of the subject based on the geometric topological data of the eyeball under the different environmental conditions measured by the measurement module, wherein the measurement module is further configured to obtain parameters of the geometric topological data of the eyeball; and the classification module is further configured to formulate a function of the parameters of the geometric topological data of the eyeball with respect to the environmental conditions, calculate a derivative of the function, and calculate a slope of the derivative.

2. The detection and classification system of claim 1, wherein, The different environmental conditions include at least two of the following environmental conditions: i) ambient atmospheric pressure; ii) pressure lower than ambient atmospheric pressure; iii) pressure higher than ambient atmospheric pressure.

3. The detection and classification system of claim 2, wherein, The different environmental conditions further include the same or different preset temperatures.

4. The detection and classification system of any one of claims 1 to 3, wherein, The detection and classification system further comprises: an environmental setting module for providing the different environmental conditions for the eyeball of the subject.

5. The detection and classification system of any one of claims 1 to 3, wherein, The measurement interval of the geometric topological data of the eyeball under the different environmental conditions measured by the measurement module is 15 to 30 seconds.

6. The detection and classification system of any one of claims 1 to 3, wherein, The geometric topological data of the eyeball includes corneal topography of the eyeball.

7. The detection and classification system of any one of claims 1 to 3, wherein, The geometric topological data of the eyeball includes corneal topography of the eyeball.

8. The detection and classification system of any one of claims 1 to 3, wherein, The geometric topological data of the eyeball includes tomographic data of the eyeball.

9. The detection and classification system of claim 1, wherein, The classification module classifies the eye condition of the subject according to the size of the slope.

10. The detection and classification system of claim 4, wherein, The head-mounted device used as the environmental setting module can be worn on the head of the subject and forms a closed internal cavity surrounding the eye of the subject together with the body surface of the subject, wherein the head-mounted device is provided with a conduit connector capable of adjusting the pressure in the closed internal cavity by controlling the inflow and outflow of gas, and the head-mounted device is provided with an observation channel at a position corresponding to the eye of the subject, so that the operator can detect the eyeball of the subject through the observation channel.

11. The detection and classification system of claim 10, wherein, The conduit connector connects a gas conduit and introduces or discharges gas into or from the closed internal cavity through the gas conduit.

12. The detection and classification system of claim 11, wherein, The pressure in the closed internal cavity is set by controlling the flow rate of the gas.

13. The detection and classification system of claim 11, wherein, The pressure in the closed internal cavity is set by controlling the composition of the gas introduced into the closed internal cavity.

14. The detection and classification system of claim 13, wherein, The gas is selected from air, water vapor and nitrogen.

15. The detection and classification system of claim 10, wherein, The observation channel is an opening hole with a transparent material installed.

16. The detection and classification system of claim 15, wherein, The opening hole is connected to an observation device through a connecting device.

17. The detection and classification system of claim 16, wherein, The observation device is selected from corneal coherence tomography instruments, corneal imaging instruments and corneal topography instruments.

Images