Choroidal imaging

Abstract

A method includes illuminating a region of a choroid of an eye of a patient with off-axis illumination from a first imaging channel that is off-axis relative to an axis of focus of the eye. The method can also include capturing an image on the choroid with the off-axis illumination from the first imaging channel offset from an image sensor in the first imaging channel. A second off-axis illumination from a second imaging channel that is off-axis from the first imaging channel and the off-axis illumination can illuminate the same or a different region of the choroid. The captured image of the choroid can be provided to a machine learning system. An indicator associated with the image can be identified based on an output of the machine learning system.

Description

Technical Field

[0001] This application generally relates to devices and processing techniques for choroidal imaging. Background Technology

[0002] Imaging the choroidal vessels of the eye is a challenging problem. For example, the pigment and / or retinal pigment epithelial cells (RPE) in the retina can protect or obscure the choroidal vessels. Furthermore, or otherwise, illumination reflections on the retina and / or retinal pigment epithelial cells may prevent the formation of a clear image within the choroidal vessels.

[0003] The topics described herein are not limited to resolving any defects or to embodiments that operate solely in a working environment as described above. Rather, this background section merely provides examples of a particular field of technology in which the embodiments described herein can be implemented. Summary of the Invention

[0004] One or more embodiments of this disclosure can include a method comprising: illuminating a region of the choroid of a patient's eye with off-axis illumination from a first imaging channel and off-axis illumination from a second imaging channel, originating from the first imaging channel. The method further includes capturing an image of the choroid using an image sensor in the first imaging channel, wherein the off-axis illumination from the first imaging channel is offset from the image sensor within the first imaging channel. The method may further include identifying one or more metrics based on the choroid image. The method may also include providing the captured image and one or more metrics to a machine learning system. Attached Figure Description

[0005] The embodiments will be described and explained with reference to the additional features and specific details shown in the accompanying drawings, wherein:

[0006] Figure 1A An example of a channel in a wide-area multi-channel imaging device is shown;

[0007] Figure 1B It shows Figure 1A Examples of illumination and imaging beams in wide-area multi-channel imaging devices;

[0008] Figure 2 Examples of wide-area images covered by a standard fundus camera and optical coherence tomography (OCT) are shown;

[0009] Figure 3A and 3B This shows two instances of views of an eye captured by two different imaging devices;

[0010] Figure 3C It shows Figure 3A A close-up view of the image;

[0011] Figure 4A and 4B Two additional instances of eye views captured by two different imaging devices are shown;

[0012] Figure 5A and 5B Two additional instances of eye views captured by two different imaging devices are shown;

[0013] Figure 6 An additional view instance of an eye captured by a wide-area multi-channel imaging device is shown;

[0014] Figure 7 This is a flowchart of a method example 700 for choroidal imaging of a patient's eye; and

[0015] Figure 8 An example of a computing system is shown. Detailed Implementation

[0016] This disclosure relates particularly to the use of a wide-area multichannel imaging apparatus for capturing internal regions of the eye. Certain imaging techniques and imaging procedures can be used to provide a robust and expansive view of the choroid and / or choroidal vessels. For example, specific illumination wavelengths, depths of focus, and / or imaging procedures can enhance the visibility of choroidal vessels compared to previous methods of capturing images of choroidal vessels. In another example, using this multichannel imaging apparatus with both illumination and imaging rays off-axis enables better imaging of the choroid. Compared to existing imaging apparatuses, because the illumination is off-axis or polarized, using this imaging apparatus reduces direct reflections from the retinal surface and / or retinal pigment epithelial cells, resulting in better visibility of choroidal vessels, especially in the macula, extending to more distant edges.

[0017] The choroid comprises the tissue located between the retina and the sclera. It includes multiple layers of vascular systems of varying sizes connecting tissues and membranes. The choroid includes Halle's layer with larger diameter vessels, Zatkun's layer with medium-diameter vessels, the choroidal capillary layer with capillaries, and Bruch's membrane as the innermost layer. The choroid is typically between 0.1 and 0.2 millimeters thick, with its thickest portion located at the back of the eye. Because the choroid is located beneath the retina and retinal pigment epithelium, it and its vessels are difficult to image. Specifically, the retina and retinal pigment epithelium absorb most of the light in the 200-600 nanometer wavelength range. Furthermore, the fluid in the eye absorbs a significant amount of light in the 900-1000 nanometer wavelength range. In individuals with light-colored eyes (e.g., blue eyes), conventional fundus cameras can capture a certain number of choroidal vessels due to the reduced absorbance and reflectance of the retina and retinal pigment epithelium. However, even when a standard fundus camera uses the target wavelength of illumination, a large number of choroidal vessels may still be obscured by the retina and retinal pigment epithelial cells.

[0018] Figure 1A An example of a wide-area multi-channel imaging device 100a is shown. Figure 1B An example of illumination and / or imaging light associated with device 100b is shown. This device may be as described in U.S. Non-Provisional Application No. 16 / 698,024, the disclosure of which is incorporated herein by reference in its entirety. However, this device is merely an example, and the embodiments described herein are not limited to its use. Figure 1A and 1B The device shown captures an image. Conversely, this disclosure can be applied to any device that uses multiple imaging channels.

[0019] Figure 1A An example of a channel 110 of a wide-area multi-channel imaging device 100a according to one or more embodiments of the present disclosure is shown. The imaging device may include multiple imaging channels 110. Each channel 110 may include: a light trail 115, a glass window 120, one or more glass lenses 122 and 124, one or more polarizing filters 130, one or more alternating lenses 140, 142 and 144, a camera aperture 150, and one or more camera sensors 152. Channels 110 may be off-axis from the central axis of the device (e.g., an axis extending from the pupil of the eye). In other words, channel 110 may cooperate with other similar channels oriented at an angle relative to the eye, and these multiple channels cooperate to form an image of the eye. For example, channel 110 may image over the overlapping area of ​​the eye, allowing a large portion of the interior of the eye to be imaged. Figure 3A , Figure 4A , Figure 5A , Figure 6Several examples of images captured by the imaging device are shown.

[0020] Figure 1B An example of illumination and imaging ray symbols for a wide-area multi-channel imaging apparatus according to one or more embodiments of the present disclosure is shown in FIG1. Figure 1B A multi-channel imaging system 100b is illustrated, comprising a first imaging channel 160, a second imaging channel 162, a third imaging channel 164, a first light track 170, a second light track 172, and a third light track 174 for imaging a first region 180 and a second region 185. Further details of an example of this device, including the operation of the imaging channels and illumination sources, are described in U.S. Non-Provisional Application No. 16 / 698,024. Imaging device 100b can be any imaging device with off-axis illumination from an image capture path, wherein the image capture path has multiple off-axis imaging channels. For example, many imaging devices use an imaging path coaxial with the pupil of the eye and use illumination along a similar axis (such as peripheral illumination along the imaging path). Imaging device 100b may include illumination that is angled and offset relative to the imaging path. In some embodiments, the illumination may originate together from different imaging channels, or from the same imaging channel but offset or angled relative to the imaging path, and / or combinations thereof. For example, an area aligned with the imaging path can be illuminated by another imaging channel, and peripheral areas can be illuminated by an offset illumination source within the same imaging channel as the imaging device. Furthermore, the imaging channel can be offset from the axis of the eye's focal point. In other embodiments described, the imaging channel can be off-axis from the axis of the eye's focal point, and the illumination of the imaging channel can also be off-axis from the imaging channel. In some embodiments, using off-axis illumination allows for less illumination directly reflected by the retina and / or retinal pigment epithelial cells, enabling the imaging device to better capture choroidal vessels with off-axis illumination.

[0021] Figure 2An example of a wide-field image 200 covered by a standard fundus camera and optical coherence tomography (OCT) according to one or more embodiments of the present disclosure is shown. The image 200 as a whole may represent the coverage area of ​​the wide-field multichannel imaging apparatus described in the present disclosure and U.S. Non-Provisional Application 16 / 698,024. For example, a solid circle 210 may represent the area captured by a standard fundus camera (e.g., approximately fifty degrees). Another example, a dashed square 220 may represent the area captured by optical coherence tomography. It can be seen that by observing the contrast between the solid circle and the wide-field image 200, the wide-field image 200 captures an area much larger than the eye, containing a larger field of view compared to that captured by a standard fundus camera or optical coherence tomography. By capturing a larger area, the model and features of the entire or nearly entire choroid can be imaged and / or analyzed, whereas an image the size of the solid circle 210 or the dashed square 220 only provides information about a very small and specific area of ​​the choroid. While a specific view acquired by a standard fundus camera and / or optical coherence tomography (OCT) might be useful for certain purposes, a wider macroscopic view might be useful for other situations and purposes. For example, a lateral slice view from OCT can be used to measure choroidal thickness, whereas a lateral slice view at one location cannot provide the same information. Figure 3A , Figure 4A , Figure 5A and / or Figure 6 The macroscopic layer view is shown. In some embodiments, the macroscopic layer image may capture at least 60 percent, at least 70 percent, at least 75 percent, at least 80 percent, at least 85 percent, at least 90 percent, at least 95 percent, and / or 100 percent of the choroid. Furthermore, artificial intelligence algorithms may derive at least some key information from more dispersed or off-center portions of the fundus image. For example, ultra-wide field cameras (such as those consistent with this disclosure) may provide useful information for artificial intelligence purposes.

[0022] Figure 3A and 3B Two instances of eye views are shown, illustrating different views captured by two different imaging devices. Figure 3A The image 300a shown is being... Figure 1B The image captured by the imaging device 100 shown. Figure 3B The image 300b shown is of the same eye captured by a wide-area scanning laser ophthalmoscopy (SLO) imaging device. Figure 3C It shows Figure 3A A close-up view of part of 300c, Figure 3CA close-up view 300c shows the choroidal vessels 310 and the retinal vessels 320. It can be seen that the wide view 310 of the choroidal vessels is visible in image 300a. Therefore, as... Figure 3A As shown, a macroscopic layer view of the choroid in the main view can be obtained using the imaging device 100 shown in Figure 1. This is comparable to a standard fundus camera (such as...). Figure 2 (in solid circle 210) or optical coherence tomography (such as Figure 2 (Comparison of dashed squares 220 in the image) Macroscopic view information allows for a broader view of the choroidal vascular system.

[0023] In some embodiments, different views of the choroid can be acquired during the processing of macroscopic layer views. For example, an image (e.g., image 300a) can be rendered with certain wavelengths highlighted or filtered. This makes specific portions of the choroid more visible. For example, when rendering an image to highlight choroidal vessels, longer wavelengths (such as red light, near-infrared, infrared, etc.) can be highlighted. In other embodiments, broadband light sources can be used for illumination; for example, a bright white light-emitting diode (LED) illumination source also covers at least a portion of the infrared spectrum. After data is captured from the imaging sensor, certain wavelengths can be highlighted or filtered when the data is displayed on a monitor. For example, when rendering RGB values ​​with a given pixel, red values ​​can be highlighted while blue and green values ​​can be toned down.

[0024] In some embodiments, image processing can process data captured by an image sensor. The image processing techniques include sharpening techniques. For example, an unsharpened mask can be applied to an image to enhance brightness differences along detected edges. During this image processing, the sharpening radius of the detected edges can typically be used to correspond to choroidal vessels or to a choroidal vascular layer to be observed / analyzed. For example, different sharpening radii of the edges can be used to highlight target layers of the choroid with a target radius, such as Halle's layer (larger vessels correspond to larger radii) and / or the choroidal capillary layer (capillaries correspond to smaller radii).

[0025] In some embodiments, a series of images can be captured. In some embodiments, the series of images can all share a common depth of focus and / or illumination wavelength. In the described and other embodiments, the series of images can be combined into a video. This video can allow the capture of flow in the choroidal vessels, for example, to visualize a user's pulse or heartbeat. In some embodiments, the series of images can be captured with different depths of focus. For example, a series of images can be captured with the focus located at multiple depths in the choroid, so that different layers of the choroidal vascular system are in focus and can be seen more clearly in different images (e.g., the first image can focus most on the choroidal capillaries at a certain depth, and the second image can focus most on the Halle's layer at a certain depth).

[0026] In some embodiments, different metrics of the choroid can be captured or rendered through computer processing of choroidal imaging. Examples of these metrics can include the average choroidal vessel diameter, which covers all choroidal vessels or a subset of choroidal vessels defined by the range of choroidal lumen diameter or their location in the image. For example, the outer diameter (e.g., vessel diameter) of all vessels in a region of the image can be determined, and the number of vessels can be used to determine the average vessel diameter. Another example of a metric can include the average choroidal vessel tortuosity, which covers all choroidal vessels or a subset of choroidal vessels defined by the range of choroidal lumen diameter or their location in the image. For example, the length of a given vessel at a certain distance can be measured and set to a ratio (e.g., Lvesseil distance can yield a numerical value of tortuosity) to determine the tortuosity of a given vessel, and the average tortuosity of all choroidal vessels in the entire image or a region of the image. Additional examples of these metrics can include the ratio of choroidal vessel diameter to retinal vessel diameter, covering all retinal and choroidal vessels, or a subset of some of them. Another example of these metrics may include the ratio of choroidal vessel tortuosity to retinal vessel tortuosity, covering all retinal and choroidal vessels, or a subset thereof. Another example of these metrics may include classification based on choroidal branching models (e.g., number of branches per unit distance, branch directionality, target indication in a number of predefined choroidal vessel models, etc.) or choroidal vessel density (e.g., number of vessels per unit distance, etc.). In the described and other embodiments, these multiple metrics can be determined automatically or manually. Any other metrics may be used and considered for inclusion in this disclosure. In some embodiments, specific regions of a macroscopic tomographic view of the choroid may be manually selected for analysis. For example, a region may be selected to determine choroidal vessel diameter and / or retinal vessel diameter.

[0027] In some embodiments, one or more indicators of this disclosure may be used at an absolute level (e.g., they may be determined as a single event or analysis, conveniently determining a patient's general or ocular condition regardless of the availability of clinical or demographic data). For example, a patient may come in for a routine eye exam, and images of the choroid may be captured as part of the eye exam, from which one or more indicators may be determined. Furthermore, these indicators can be used to calculate changes before and after an intervention, thereby understanding the impact of the intervention. For example, images may be taken before and after dialysis, during which a large amount of fluid is removed from the patient, and images taken before and after dialysis based on these indicators can help determine the effectiveness of fluid removal in reducing fluid overload. In another instance, a single image taken before an intervention can help determine the temperature of the body fluid state, thereby determining how much fluid needs to be removed during dialysis. In some embodiments, other conditions or interventions may be analyzed and considered based on choroidal indicators.

[0028] In some embodiments, the images of indicators and / or choroidal vessels can be provided to a machine learning system. In the described and other embodiments, the machine learning system can utilize these indicators and / or images to identify patient-related models and features that are not readily apparent to human vision. For example, applying machine learning to images captured using conventional fundus cameras has been shown to identify gender, smoking status, etc., with high accuracy, even features that cannot be identified by human analysis. In the described and other embodiments, the machine learning system can identify correlations, models, resolution matrices, etc., from choroidal images. For example, a set of training data can be provided to a machine learning system containing one or more choroidal images and / or indicators of an individual, along with other factors of that individual (e.g., disease conditions, health habits, genetic traits, etc.). The machine learning system can then analyze and determine the models and correlations between the individual's factors and the choroidal images and / or indicators. As another example, various artificial intelligence algorithms can be trained on such sets of images (preferably large sets) to specifically identify specific diseases or endpoint measurements using choroidal parameters based on identified correlations. These correlations can be related to different disease conditions, health habits, fluid levels, genetic diseases, or disease predispositions. For example, risk assessment of specific diseases based on a series of symptoms combined with choroidal imaging, such as the risk of cerebrovascular accidents (e.g., stroke) in people with stroke-like symptoms (or transient ischemic attacks), can help determine whether individuals with these symptoms urgently need intensive testing.

[0029] Figure 4A and 4B Two additional example images 400a and 400b of the eye captured using two different imaging devices are shown. (Used to capture...) Figure 4AImage 400a and Figure 4B The 400b imaging device can be used separately with the image capture device. Figure 3A Image 300a and Figure 3B The imaging equipment of the 300b is the same as or similar to that of the other two.

[0030] Compared to image 300a, image 400a shows a different image of the other eye. Furthermore, Figure 4A The red hue of the image shown is greater than Figure 3A The enhancement shown is to a greater extent.

[0031] Figure 5A and 5B Two additional example images 500a and 500b of an eye captured using two different imaging devices according to one or more embodiments of this disclosure are shown. (For capturing...) Figure 5A Image 500a and Figure 5B The 500b imaging device can be used to capture images. Figure 3A Image 300a and Figure 3B The imaging equipment of the 300b is the same as or similar to that of the other two.

[0032] Figure 6 An additional view instance 600 is shown, in which the eye is captured by a wide-area multi-channel imaging device; used for capturing Figure 6 The image 600 imaging device can be used to capture Figure 3A The imaging equipment of the image 300a is the same or similar.

[0033] Imaging devices for capturing images at resolutions of 300a, 400a, 500a, and / or 600a (e.g., Figure 1B Imaging device 100 may be significantly cheaper than imaging devices that capture images 300b, 400b, and / or 500b. For example, imaging devices for capturing images 300a, 400a, 500a, and / or 600 may require expensive multi-wavelength lasers and expensive, extensive lens systems. Furthermore, such devices may require a larger area and need to be mounted on a table. Conversely, imaging devices for capturing images 300a, 400a, 500a, and / or 600 (e.g., Figure 1B The imaging device 100 can be much smaller and use much cheaper illumination (e.g., white light-emitting diodes compared to multi-wavelength laser systems). Furthermore, imaging devices for capturing images 300a, 400a, 500a, and / or 600a (e.g., Figure 1B The imaging device 100 can have a much smaller waveform factor, including handheld devices or portable and / or mountable devices. Figure 7This is a flowchart of an example method 700 for imaging the choroid of a patient's eye according to at least one embodiment described in this disclosure. Method 700 can be performed by any suitable system, instrument, or device. For example, in Figure 1A The imaging device and / or computing device shown in / 1B (e.g.) Figure 8 (As shown) can perform one or more operations related to method 700. Although shown in discontinuous blocks, the steps and operations associated with one or more blocks of method 700 can be divided into additional blocks, combined into fewer blocks, or eliminated, depending on the specific implementation.

[0034] Method 700 can begin with block 710, wherein the choroid of the patient's eye can be illuminated using off-axis illumination from the imaging channel. The choroid of the eye can be illuminated as described above. Figure 1A and 1B It was irradiated as described.

[0035] In block 720, an image of the choroid can be captured using an image sensor in the imaging channel. An image of the choroid can be captured as described above. Figure 1A and 1B It was captured as described.

[0036] In block 730, the first wavelength of light can be filtered out from the captured image. The first wavelength of light can be filtered out as described above. Figure 3A and 3B The description is used to filter out images captured in the same way.

[0037] In block 740, the second wavelength of light can be highlighted in the captured image. The second wavelength of light can be highlighted as described above. Figure 3A and 3B The description stands out in the captured image.

[0038] In block 750, the captured image can be provided to a machine learning model. As described in this disclosure, the captured image can be provided to a machine learning model.

[0039] In block 760, one or more indicators related to the image of the choroid can be identified. As described in this disclosure, the one or more indicators related to the image of the choroid can be identified.

[0040] Method 700 can be modified, added to, or deleted without departing from the scope of this disclosure. For example, specifying different elements in the behavior described above is to help explain the concepts described herein, but is not limited thereto. Furthermore, method 700 may include any number of other elements or may be implemented in other systems or scenarios not described.

[0041] Figure 8An example of a computing system 800 is shown, according to at least one embodiment described in this disclosure. The computing system 800 may include a processor 810, a memory 820, a data storage 830, and / or a communication unit 840, all of which may be communicatively coupled. Figure 7 Any or all operations of method 700 can be implemented in a computing system consistent with computing system 800. Another example is that computing systems, such as computing system 800, can be coupled to... Figure 1A and 1B The imaging device shown is and / or is part of the imaging device.

[0042] Typically, processor 810 can include any suitable special-purpose or general-purpose computer, computing entity, or processing device, encompassing a wide variety of hardware or software models, and can be configured to execute instructions stored on any suitable computer-readable storage medium. For example, processor 810 can include a microprocessor, microcontroller, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or any other digital or analog circuitry configured to interpret and / or execute program instructions and / or process data.

[0043] Although Figure 8 While shown as a single processor, it should be understood that processor 810 can include any number of processors distributed across any number of network or physical locations, configured to individually or collectively perform any number of operations described herein. In some embodiments, processor 810 is capable of interpreting and / or executing program instructions and / or processing data stored in memory 820, data storage 830, or both memory 820 and data storage 830. In some embodiments, processor 810 is capable of retrieving program instructions from data storage 830 and loading program instructions into memory 820.

[0044] After the program instructions are loaded into memory 820, processor 810 is able to execute program instructions, such as executing... Figure 7 Method 700 provides instructions for any steps related to this process. For example, processor 810 is capable of obtaining relevant instructions such as: obtaining training code, extracting features from the training code, and / or pairing the extracted features with natural language code vectors.

[0045] Memory 820 and data storage 830 may include a computer-readable storage medium or one or more computer-readable storage media for carrying or storing computer-executable instructions or data structures. The computer-readable storage medium may be any suitable medium accessible by a general-purpose computer or a special-purpose computer, such as processor 810. For example, memory 820 and / or data storage 830 may store identified metrics (e.g., in...) Figure 7 (One or more indicators identified in block 760). In some embodiments, computing system 800 may or may not include either memory 820 and data storage 830. For example, but not as a limitation, the computer-readable storage medium may include permanent computer-readable storage media, including random access memory (RAM), read-only memory (ROM), electronically erasable programmable read-only memory (EEPROM), read-only optical disc memory (CD-ROM) or other optical disc memory, or other disk memory, flash memory devices (such as solid-state storage devices), or any other storage medium that can be used to carry or store required program code, which is accessible to a general-purpose computer or a special-purpose computer in a computer-executable form or in the form of data structures. Combinations of the above storage media may also be included within the scope of computer-readable storage media. Computer-executable instructions may include, for example, instructions and data configured to cause processor 810 to perform an operation or a set of operations.

[0046] The communication unit 840 may include any component, device, system, or combination thereof configured to transmit and receive information over a network. In some embodiments, the communication unit 840 is capable of communicating with devices in other or the same locations, or even with other components within the same system. For example, the communication unit 840 may include a modem, a network interface card (NIC) (wireless or wired), an optical communication device, an infrared communication device, a wireless communication device (e.g., an antenna), and / or a chipset (e.g., a Bluetooth device, an 802.6 device (e.g., a metropolitan area network (MAN)), a wireless network device, a global microwave interconnection access device, a mobile communication device, or others), and / or similar. In this disclosure, the communication unit 840 is capable of allowing data to be exchanged over a network and / or any other device or system. For example, the communication unit 840 is capable of allowing system 800 to communicate with other systems, such as computing devices and / or other networks.

[0047] Those skilled in the art, upon reviewing this disclosure, will recognize that modifications, additions, or deletions to system 800 do not depart from the scope of this disclosure. For example, system 800 may include, to varying degrees, the components that have been shown and disclosed.

[0048] It is important to understand that when choroidal imaging is used in conjunction with AI for analysis, correlation detection, etc., it is understood that other imaging techniques can also be combined with or used in conjunction with choroidal imaging. For example, in addition to choroidal imaging, retinal vascular imaging can also be considered or analyzed together with corresponding choroidal imaging. In the described and other embodiments, the identification of correlations, disease states, etc., can be based on both choroidal imaging and retinal vascular imaging. For example, the subject matter of this disclosure is illustrated according to several aspects described below. For convenience, examples of various aspects of this subject matter are described as numbered examples (1, 2, 3, etc.). The following are provided as examples but do not limit the subject matter. It is noteworthy that any dependent examples or parts can be combined and placed in a separate example, such as examples 1, 2, and 3. Other examples can be represented in a similar manner. The following is a non-limiting summary of some examples presented herein.

[0049] Example 1 includes a method comprising illuminating a region of the choroid of a patient's eye with off-axis illumination from a first imaging channel. The method also includes capturing an image of the choroid using an image sensor, wherein the off-axis illumination from the first imaging channel is offset from the image sensor within the first imaging channel. The method further includes providing the captured image to a machine learning system.

[0050] Example 2 includes a method for performing an eye examination, comprising illuminating a region of the choroid of a patient's eye with off-axis illumination from a first imaging channel, and capturing a first image of the choroid using an image sensor in the first imaging channel prior to intervention, wherein the off-axis illumination from the first imaging channel is offset from the image sensor within the first imaging channel. The method also includes identifying one or more computer-processed indicators based on the choroid image. The method further includes capturing a second image of the choroid using the image sensor in the first imaging channel after intervention, and then identifying one or more second indicators based on computer processing of the second choroid image. The method also includes comparing one or more first indicators with one or more second indicators. The method further includes identifying the effect of the intervention based on the comparison of one or more first indicators with one or more second indicators.

[0051] Example 3 includes a method for performing choroidal imaging using a handheld imaging device. The method includes illuminating a region of the choroid of a patient's eye with off-axis illumination from a first imaging channel, and capturing a first image of the choroid using an image sensor in the first imaging channel, wherein the off-axis illumination from the first imaging channel is offset from the image sensor within the first imaging channel. The method also includes identifying one or more computer-processed metrics based on the choroidal image. The method further includes capturing a second image of the choroid using the image sensor in the first imaging channel, and then identifying one or more second metrics based on the computer processing of the second choroidal image. In some examples, the region of the patient's choroid illuminated may include the region of the choroid illuminated using second off-axis illumination from a second imaging channel, the second off-axis being off-axis from both the first imaging channel and the off-axis illumination. In some examples, the first imaging channel and off-axis illumination are capable of capturing a first image of the retina of the eye, and the second imaging channel and second off-axis illumination capture a second image of the choroid of the eye, the first and second images having overlapping areas. In the above examples, the first and second images can be combined into a single image having a wider field of view than both the first and second images.

[0052] Some instances include one or more additional operations that may include filtering out a first wavelength of light displayed in the captured image, which is related to a first color. In this instance, a second wavelength of light displayed in the captured image can be highlighted, which is related to a second color. In this instance, the second wavelength of light may be related to red.

[0053] In some instances, the off-axis illumination can be a broadband light source. In this instance, the broadband light source can be a bright white light-emitting diode (LED). In some instances, capturing an image of the choroid can include sharpening the captured image, wherein sharpening the captured image includes applying an unsharpened mask to the captured image. In this instance, a sharpening radius for edge detection can be determined, corresponding to a target layer of the choroidal vessels of the eye's choroid with a target size, and this sharpening radius is used to sharpen the captured image.

[0054] Some examples include one or more additional operations, which may involve capturing a series of images of the choroid. This series of choroidal images may have a common depth of focus and a common illumination wavelength. The series of choroidal images may have more than one depth of focus. The series of choroidal images can be combined to create a video of the choroid. In this example, blood flow through the choroidal vessels can be analyzed to identify the heartbeat in the choroidal video.

[0055] Some instances include one or more additional operations that may include one or more metrics based on the output of the machine learning system. These metrics may include at least one of the following: average choroidal vessel diameter, average choroidal vessel tortuosity, the ratio of choroidal vessel diameter to retinal vessel diameter, the ratio of choroidal vessel to retinal vessel tortuosity, a classification based on choroidal branching patterns, or choroidal vessel density. These metrics can be identified based on a region of a choroidal image smaller than the entire choroidal image. The machine learning system can be trained to identify at least one specific disease or endpoint measurement based on one or more identified metrics.

[0056] It should be understood that a processor can comprise any number of processors distributed across any number of networks or physical locations, configured to individually or collectively perform any number of operations described herein. In some instances, the processor is capable of interpreting and / or executing program instructions and / or processing data stored in memory. By interpreting and / or executing program instructions and / or processing data stored in memory, the device is capable of performing operations, such as those performed by the panoramic corner mirror device described herein.

[0057] Memory may include a computer-readable storage medium or one or more computer-readable storage media for carrying or having computer-executable instructions or data structures stored thereon. The computer-readable storage medium can be any suitable medium accessible to a general-purpose computer or a special-purpose computer, such as the processor. For example, but not as a limitation, the computer-readable storage medium can include permanent computer-readable storage media, including random access memory (RAM), read-only memory (ROM), electronically erasable programmable read-only memory (EEPROM), read-only optical disc storage (CD-ROM) or other optical disc storage, or other disk storage, flash memory devices (such as solid-state storage devices), or any other storage medium that can be used to carry or store required program code, in a computer-executable form or data structure accessible to a general-purpose computer or a special-purpose computer. Combinations of the above storage media may also be included within the scope of computer-readable storage media. In the described and other embodiments, the term "permanent" as used herein should be interpreted as excluding only temporary media types that are not within the scope of the patent subject matter as stated in the Federal Circuit judgment (500F.3d 1346 (Fed. Cir. 4007)). In some embodiments, computer-executable instructions may comprise, for example, instructions and data configured to cause a processor to perform an operation or a set of operations.

[0058] As is customary, the various features shown in the accompanying drawings may not be drawn to scale. The drawings presented in this disclosure are not intended as actual views of any specific instrument (e.g., device, system, etc.) or method, but are merely idealized representations illustrating various embodiments of this disclosure. Therefore, the dimensions of various features may be arbitrarily enlarged or reduced for clarity. Furthermore, some drawings may be simplified for clarity. Thus, these drawings may not depict all parts of a given device (e.g., apparatus) or all operations of a particular method. For example, dashed lines for illumination and imaging paths do not necessarily reflect a true optical design, but rather illustrate the concept of the invention.

[0059] The terms used herein, especially in the appended claims (e.g., the text of the appended claims), are generally treated as “open” terms (e.g., the term “comprising” should be interpreted as “comprising, but not limited to”, the term “having” should be interpreted as “having at least”, the term “including” should be interpreted as “comprising, but not limited to”, etc.).

[0060] Furthermore, if there is an intention to elaborate on a certain number of claims, this intention will be explicitly stated in the claims; if there is no intention, then no such elaboration will be included. For example, to aid understanding, the appended claims below may include the introductory phrases “at least one” and “one or more” to introduce the detailed description of a claim. However, the use of such phrases should not be construed as implying that a claim statement introduced by the indefinite article “a” or “a” will limit any particular claim containing such an introductory claim statement to containing only one embodiment of such a statement, even when the same claim includes the introductory phrases “one or more” or “at least one” and indefinite articles such as “a” or “a” (e.g., “a” and / or “a” should be interpreted as meaning “at least one” or “one or more”); the same applies to the use of definite articles introducing the claim statement.

[0061] Furthermore, even if the specific number of statements in the introduced claims is explicitly stated, those skilled in the art will recognize that such a statement should be interpreted as indicating at least the number of statements (e.g., the simple statement "two statements" without other modifiers indicates at least two statements, or two or more statements). Additionally, phrases such as "at least one of A, B, and C" or "one or more of A, B, and C, etc." are generally intended to include a single A, a single B, a single C, A and B together, A and C together, B and C together, or A, B, and C together, etc. For example, the use of the term "and / or" is intended to be interpreted in this manner. Furthermore, the terms "approximately" or "about" should be interpreted as values ​​within 10% of the actual value. Moreover, any separating words or phrases indicating two or more optional terms, whether in the specification, claims, or drawings, should be understood to consider the possibility of including one term, either of the two terms, or both terms. For example, the phrase "A or B" should be understood to include the possibility of including "A" or "B" or "A and B".

[0062] However, the use of such phrases should not be construed as implying that a claim statement introduced by the indefinite article “a” or “an” will limit any particular claim containing such an introduced claim statement to containing only one embodiment of such a statement, even when the same claim includes the introductory phrase “one or more” or “at least one” and the indefinite article such as “a” or “an” (e.g., “a” and / or “an” should be interpreted as meaning “at least one” or “one or more”); the same applies to the use of definite articles that introduce a claim statement.

[0063] Furthermore, the use of terms such as "first," "second," and "third" is not necessarily required in this document to indicate a specific order or number of elements. Generally speaking, terms such as "first," "second," and "third" are used as general identifiers to distinguish between two elements. Unless explicitly stated that "first," "second," and "third" signifies a specific order, these terms should not be interpreted as indicating a specific order. Moreover, unless explicitly stated that "first," "second," and "third" signifies a specific number of elements, these terms should not be interpreted as indicating a specific number of elements. For example, a first component can be described as having a first side, and a second component can be described as having a second side. The use of the term "second side" regarding the second component distinguishes that side of the second component from the "first side" of the first component, but does not imply that the second component has two sides.

[0064] All examples and conditional language detailed herein are for educational purposes and to help the reader understand the invention and the inventors' concepts for contributing to the field. These examples and conditional language are not intended to limit the examples and conditions specifically detailed above. While embodiments of this disclosure have been described in detail, it should be understood that various variations, substitutions, and modifications can be made without departing from the schemes and scope of this disclosure.

[0065] In addition to the color drawings, the drawings are also submitted in grayscale format to facilitate understanding of this disclosure.

Claims

1. A method for choroidal imaging, comprising: The area of ​​the patient's choroid is illuminated using off-axis illumination from a first imaging channel, which is off-axis relative to the eye's focal point. An image of the choroid is captured using an image sensor in the first imaging channel, and off-axis illumination from the image sensor is offset within the first imaging channel. Provide the captured images to the machine learning system; as well as One or more indicators of the choroid are identified based on the output of the machine learning system. The machine learning system is trained to identify one or more diseases based on one or more identified indicators.

2. The method of claim 1, wherein irradiating the area of ​​the patient's choroid further comprises irradiating the area of ​​the choroid using a second off-axis illumination from a second imaging channel, the second off-axis illumination being off-axis from both the first imaging channel and the off-axis illumination.

3. The method of claim 2, wherein a first imaging channel and off-axis illumination capture a first image of the choroid of the eye, and a second imaging channel and second off-axis illumination capture a second image of the choroid of the eye, the first image and the second image having overlapping regions, the method further comprising combining the first image and the second image into a single image having a wider field of view than both the first image and the second image.

4. The method according to any one of claims 1, 2, or 3, further comprising: Processing the captured image includes: filtering a first wavelength of light from the captured image, the first wavelength of light being associated with a first color; and The second wavelength of light is highlighted in the captured image, and this second wavelength is associated with a second color.

5. The method of claim 4, wherein the second wavelength of the light is associated with red.

6. The method according to any one of claims 1 to 3, wherein the off-axis illumination is a broadband light source.

7. The method of claim 6, wherein the broadband light source is a bright white light-emitting diode (LED).

8. The method according to any one of claims 1 to 3, further comprising sharpening the captured image by applying an unsharpened mask onto the captured image.

9. The method of claim 8, further comprising determining a sharpening radius for detecting an edge, the sharpening radius corresponding to a target layer of choroidal vessels of the eye choroid having a target size, the sharpening radius being used to sharpen the captured image.

10. The method according to any one of claims 1 to 3, wherein capturing images of the choroid further comprises capturing a series of images of the choroid.

11. The method of claim 10, wherein the images of the series of choroidal membranes have a common depth of focus and a common illumination wavelength.

12. The method of claim 10, wherein the images of the series of choroidal membranes have more than one focal depth.

13. The method of claim 10, further comprising combining a series of images of the choroid to create a video of the choroid.

14. The method of claim 13, further comprising identifying a heartbeat by analyzing blood flow in the choroidal vessels of a choroidal video.

15. The method according to any one of claims 1-3, 5, 7, 9 and 11-14, wherein one or more indicators comprise at least one of the following: average choroidal vessel diameter, average choroidal vessel tortuosity, ratio of choroidal vessel diameter to retinal vessel diameter, ratio of choroidal vessel tortuosity to retinal vessel tortuosity, classification based on choroidal branching pattern, or choroidal vessel density.

16. The method according to any one of claims 1-3, 5, 7, 9 and 11-14, wherein one or more indicators are capable of being identified based on a region of a choroidal image, the region of which is smaller than the entire choroidal image.

Images