Automatic OCT Capture

Abstract

An optical coherence tomography (OCT) method including receiving an input from a patient, obtaining a reference image of an object indicating a desired scan position, and obtaining a real-time image of the object, where the reference image is specific to the patient and is obtained remotely. The real-time image is registered to the reference image and the desired scan position is determined. The OCT image is automatically obtained at the desired scan position.

Description

Technical Field

[0001] Cross - reference to Related Applications This application claims the priority of U.S. Provisional Patent Application No. 63 / 365,173, entitled "Automatic OCT Capture", filed on May 23, 2022, the entire content of which is incorporated herein by reference.

Background Art

[0002] Optical coherence tomography (OCT) is a non - invasive imaging technique and is commonly used in ophthalmology. OCT utilizes the principle of interferometry to image and collect information about an object (such as the eye being targeted). Specifically, light from a light source is split into a sample arm that is reflected by the object being imaged and a reference arm that is reflected by a reference object such as a mirror. The reflected light is then combined in a detection arm to generate an interference pattern that is detected by a spectrometer or a photodiode, etc. The detected interference signal is processed to reconstruct the object and generate an OCT image.

[0003] More specifically, structural OCT images and volumes are generated by combining a number of depth profiles (A - lines, e.g., along the Z - depth direction at X - Y positions) into a single cross - sectional image (B - scan, e.g., as an X - Z or Y - Z plane), and by combining a number of B - scans into one volume. These depth profiles are generated by scanning along the X and Y directions. A frontal image of the X - Y plane can be generated by flattening the volume in all or part of the Z - depth direction, and a C - scan image may be generated by extracting a slice of the volume at a given depth.

[0004] One application of OCT imaging is in ophthalmology to diagnose various eye conditions and irregularities. During the examination, it is common for the physician to determine the locations where additional study and / or imaging is needed. The physician usually indicates these locations to the lab technician, who then performs an OCT scan of the desired location. Therefore, the resulting OCT image depends on the lab technician's skill level and their understanding of the physician's requirements. In other words, if the OCT image is insufficient, for example, if it was taken at a location other than the desired location, another OCT image may be required.

[0005] Furthermore, patients with eye diseases generally require repeated eye scans over a period of time. This is usually accomplished through regular checkups or scans at the doctor's office. However, repeated scans are time-consuming and may require scheduling time for both the doctor and the technician. [Overview of the project] [Means for solving the problem]

[0006] According to one example of the present disclosure, the method includes receiving input from a patient, and upon receiving the input: obtaining an existing reference image of the object from a remote database which indicates a desired scan position; obtaining personal information and / or scan settings relating to the patient from the remote database which are associated with the patient's unique existing reference image; obtaining a real-time image of the object; registering the real-time image with the existing reference image; determining a desired scan position on the real-time image based on the registration; and automatically obtaining an OCT image of the object at the desired scan position according to the obtained personal information and / or scan settings.

[0007] In various embodiments of the above example, the existing reference image is one initially acquired by a physician; the real-time image is an OCT frontal image; the method further comprises authenticating the patient based on input from and acquired personal information from the patient; registering the real-time image and determining the desired scan position on the real-time image are performed by a machine learning system; the OCT image at the desired scan position is automatically acquired based on whether the desired scan position is within a threshold range of the center of the real-time image; the method further comprises determining whether the desired scan position is not within a threshold range of the center of the real-time image, acquiring a second real-time image of the object, registering the second real-time image as a reference image, and determining the desired scan position on the second real-time image based on the registration of the second real-time image; the scan settings include a patient-specific scan pattern, and the OCT image is automatically acquired according to the scan pattern; the method further comprises aligning the OCT imaging system according to the desired scan position; and / or the object is an eye.

[0008] In another example, the system comprises an optical coherence tomography (OCT) imaging system and one or more processors; the one or more processors are configured to collectively receive input from a patient, and upon receiving input: in response to the input from the patient, retrieve an existing reference image of the object from a remote database that indicates a desired scan position; retrieve personal information and / or scan settings about the patient from the remote database, which are associated with the patient's unique existing reference image; acquire a real-time image of the object; register the real-time image with the reference image; determine a desired scan position on the real-time image based on the registration; and automatically acquire an OCT image of the object at the desired scan position using the OCT imaging system according to the acquired personal information and / or scan settings.

[0009] In various embodiments of the above example, the reference image is initially acquired by a physician; the real-time image is an OCT frontal image acquired using the OCT imaging system; one or more processors are further collectively configured to authenticate the patient's use of the system based on patient input and acquired personal information; the real-time image is registered to the reference image by one or more processors configured as a machine learning system; an OCT image at a desired scan position is automatically acquired based on whether the desired scan position is within a threshold range of the center of the real-time image; one or more processors are further collectively configured to determine if the desired scan position is not within a threshold range of the center of the real-time image, acquire a second real-time image of the object, register the second real-time image to the reference image, and determine a desired scan position on the second real-time image based on the registration of the second real-time image; the scan setting includes a patient-specific scan pattern, and the OCT image is automatically acquired according to the scan pattern; one or more processors are further collectively configured to align the OCT imaging system according to the desired scan position; and / or the object is an eye. [Brief explanation of the drawing]

[0010] [Figure 1] Figure 1 shows a schematic diagram illustrating an example of an optical coherence tomography system in this disclosure. [Figure 2A] Figure 2A shows an example of an automated imaging terminal according to this disclosure. [Figure 2B] Figure 2B shows an example of an automated imaging terminal according to this disclosure. [Figure 3] Figure 3 shows an example of the method relating to this disclosure. [Figure 4] Figure 4 shows an example of the method relating to this disclosure. [Figure 5A] Figure 5A shows an example of a reference image. [Figure 5B] Figure 5B shows an example of a reference image. [Figure 5C] Figure 5C shows an example of a reference image. [Figure 6] Figure 6 shows an example of the registered technology of this disclosure. [Figure 7] Figure 7 shows an example of an image illustrating the proximity threshold. [Figure 8] Figure 8 shows a series of example OCT images. [Figure 9] Figure 9 shows an example of a real-time image. [Modes for carrying out the invention]

[0011] With the foregoing in mind, this disclosure relates to automated image capture, particularly OCT image capture. More specifically, this disclosure relates to automated OCT imaging, for example, by using a reference image.

[0012] Using the methods and devices described below, OCT images can be acquired without manual assistance or under the direction of a technician. Automated OCT imaging reduces errors caused by manually selecting scan locations, such as imaging in the wrong location. Furthermore, automated OCT scanning can facilitate regular OCT imaging (e.g., monitoring disease progression, post-operative analysis) without requiring a technician / physician to perform the scan. This results in time savings for both patients and technicians / physicians. Moreover, automated OCT imaging enables a more convenient process for patients, freeing them from the constraints of clinic hours or technician / physician availability.

[0013] Generally, automated OCT imaging improves efficiency, at least partially, by relying on reference images unique to each patient. This can reduce scan time, improve the success rate of generating acceptable images, and decrease the number of scans required. These unique reference images are used as ground truth for known conditions, in other words, to represent the known location of the patient's condition. In contrast, a "generic" solution, for example, may utilize raster scanning techniques to scan the entire eye, since the individual conditions concerning the patient are not necessarily known to the automated imaging system. As a result, such systems and methods tend to have lower success rates, require more scans and scan time, and are generally less efficient. By using unique reference images, it is possible to create OCT images focused on specific patient conditions, potentially providing automated, customized imaging scans of patients without the need for a physician.

[0014] Referring to Figure 1, the OCT imaging system includes a light source 100. Light generated by the light source 100 is split, for example, by a beam splitter (as part of the interferometer optical system 108) and sent to a reference arm 104 and a sample arm 106. The light in the sample arm 106 is backscattered or otherwise reflected by an object such as the retina of the eye 112. The light in the reference arm 104 is backscattered or otherwise reflected by a mirror 110 or a similar object. The light from the sample arm 106 and the reference arm 104 is recombined in the optical system 108, and the corresponding interference signal is detected by a detector 102. The detector 102 may be a spectrometer, a photodetector, or any other photodetector. The detector 102 outputs an electrical signal corresponding to the interference signal to a processor 114, where it can be stored and processed in OCT signal data.

[0015] The processor 114 may then further generate corresponding structural or angiographic images or volumes, or otherwise perform data analysis. The processor 114 may also be associated with an input / output interface (not shown) which includes a display for outputting the processed images or information related to the analysis of those images. The input / output interface may include hardware such as buttons, keys, or other controls for receiving user input to the system. In some embodiments, the processor 114 may also be used to control the light source and the imaging process.

[0016] Figure 2A shows an automated imaging terminal 200 of the present disclosure. The imaging terminal 200 shown in the figure comprises a computer 202 including at least one processor 204, local storage 206a, and an input / output (I / O) device 208. The I / O device 208 may be any input / output device that enables communication and selection by a user or patient, such as a keyboard, mouse, selection buttons, LED display, or touchscreen. In some embodiments, the I / O device 208 includes a wireless communication device that communicates using wireless communication standards such as Bluetooth or Wi-Fi and can communicate with a portable device such as a mobile phone. The I / O device 208 may also communicate with a remote database 206b via a wireless communication standard, Ethernet, or Internet connection. The remote database 206b may be a cloud database, an on-premise database, or similar.

[0017] The automated imaging terminal 200 further includes a dedicated real-time imaging system 210 (fundus camera, IR camera, SLO camera, or the like), and an OCT imaging system 212. The OCT imaging system 212 may be the one discussed above and shown in FIG. 1. The real-time imaging system 210 and the OCT imaging system 212 can share a viewport 211, which can be accessed by a patient for using the automated imaging terminal 200. The viewport 211 may include at least an optical system configured to image a patient's eye by both the real-time imaging system 210 and the OCT imaging system 212.

[0018] In some embodiments, such as those shown in FIG. 2B, the automated imaging terminal 200 does not include a dedicated real-time imaging system 210. Instead, the OCT imaging system 212 also functions as a real-time imaging system by acquiring real-time high-speed anterior OCT images or the like.

[0019] The computer 202 communicates with the real-time imaging system 210 and the OCT imaging system 212 and can receive information from the real-time imaging system 210 and the OCT imaging system 212. For example, images acquired by the real-time imaging system 210 and the OCT imaging system 212 may be analyzed by at least one processor 204 (processing may be distributed among one or more processors in any manner), stored in the local storage 206a, and / or stored in the remote database 206b. The at least one processor 204 can also adjust various camera functions and alignments of the imaging systems 210, 212 having the viewport 211 by using computer-generated commands or by controlling physical actuators and motors.

[0020] The automated imaging terminal 200 may be in the design of a kiosk or the like and can be placed in a public place for easy access. Patients can walk up to the public automated imaging terminal 200 and receive regular eye scans at their convenience without the need to schedule an appointment with, for example, a technician or doctor. The automated imaging terminal 200 can automatically acquire OCT images from a desired scan position indicated by a reference image specific to the patient without operator input.

[0021] The reference image may be various types of images and can be acquired in various ways. For example, as shown in FIG. 5A, a doctor can manually mark a desired scan position within the chart drawing 510. The chart drawing 510 is a basic drawing or a simplified depiction of the human eye and is marked (e.g., with an "X") to indicate the desired scan position relative to anatomical landmarks. Additionally, or alternatively, the reference image can be acquired using a fundus camera that generates a fundus image 512 as shown in FIG. 5B. This fundus image can also be marked (e.g., with an "X") to indicate the target scan position. The reference image may be an OCT image (e.g., a frontal image, a structural C scan, an angiography image, or the like) 514 as shown in FIG. 5C. The frontal OCT image 514 may be acquired using an OCT imaging system as shown in FIG. 1. As described above, the OCT image 514 can be marked (e.g., with an "X") to indicate the desired scan position.

[0022] As described above, the reference image can represent prior knowledge regarding the patient's medical condition. However, in some embodiments, the reference image can be collected and analyzed by the automated imaging terminal 200 itself or a similar system.

[0023] In any case, the scan location is marked on the reference image to guide subsequent OCT imaging. In the case of an a priori reference image, the scan location may be manually marked by a physician or automatically identified by analysis of the reference image. A physician may manually mark the reference image on a copy of a fundus photograph using computer software or a writing instrument. The desired scan location may be indicated using colored pixels or other marks, and may be stored as coordinates on the XY axes (e.g., as digital coordinates), or as specific pixel location information or similar. The reference image may be patient-specific and therefore unique to each patient. For example, the reference image may indicate a specific desired scan location for observing retinopathy in a particular patient. In some embodiments, the reference image may indicate a general location, for example, a desired scan location near the optic nerve for observing the progression of glaucoma.

[0024] The scan location may be automatically determined and marked, for example, based on the analysis of a reference image. In some embodiments, the automated imaging terminal 200 may utilize image processing techniques such as computer vision and / or machine learning to determine a region of interest in a real-time fundus image acquired by the real-time imaging system 210 or a real-time frontal OCT image acquired using the OCT imaging system 212. The computer 202 and / or processor 204 may utilize such image processing techniques, including computer vision and machine learning. The region of interest or desired scan location may be a specific medical condition of the patient.

[0025] The reference image may be input to a machine learning system trained to identify regions of interest based on anomalies within the image, for example. Such a technique may be described in U.S. Patent No. 11,132,797, titled "Automatically Identifying Regions of Interest of an Object from Horizontal Images Using a Machine Learning Guided Imaging System," which is incorporated herein by reference in its entirety, and / or may be described in U.S. Patent Application 16 / 552,467, titled "Multivariate and Multi-Resolution Retronal Image Anomaly Detection System," which is incorporated herein by reference in its entirety.

[0026] The acquisition and marking of reference images are performed during the patient's examination and may be saved for subsequent use, for example, in the patient's physical or virtual file. The virtual file may be stored in a remote database 206b, such as the computer's local memory, an on-premises database, or cloud-based storage. For example, the patient can have their physician save the reference images on a file. The physician can use the techniques described above to indicate desired scan locations on the reference images. The reference images with the desired scan locations may be stored in the cloud or otherwise in the remote database 206b for access by the automated imaging terminal 200.

[0027] Referring to Figure 3, the patient can initiate the automated capture 301 by using a button on the device, such as a start button, or by accessing the automated imaging terminal 200 using a personalized login. In some embodiments, the patient can use their personal mobile phone to scan a machine-readable optical image, such as a QR code, located on or near the automated imaging terminal 200. The QR code can direct the user to a web application or mobile app or generate a text message where the patient can sign in to their personal account and indicate which automated imaging terminal 200 they are located on. For example, the patient can indicate their location using the Global Positioning System (GPS), prompts from the application, the GPS location of the automated imaging terminal 200, or a unique QR code associated with a specific automated imaging terminal 200.

[0028] The automated imaging terminal 200 can then communicate with a remote database 206b via the Internet or another network to obtain patient reference images, personal information, scan settings, or similar information 302. For example, scan settings may be patient-specific and may include resolution, brightness, saturation, contrast, size, scan pattern, or similar image settings that can be used when the real-time imaging system 210 or OCT imaging system 212 acquires images / scans. Personal information may include name, sex, age, height, weight, medical history, and / or pathological information and similar information. Furthermore, for example, additional instructions may include the starting center position of the real-time imaging system 210 or OCT imaging system 212, an indication of the number of OCT images or scans to be acquired, the type of registration method, or other information regarding the acquisition of real-time images or OCT images.

[0029] In some embodiments, the use of the automated imaging terminal 200 may first require patient authentication. Authentication can be determined in various ways. For example, the automated imaging terminal may authenticate the patient if the patient has reference images on a file used by the owner / operator of the automated imaging terminal 200. In particular, after the patient initiates automated capture 301, the automated imaging terminal 200 then communicates with a remote database 206b, which may contain patient information such as patient ID, login, name, address, or similar. The remote database 206b can use this patient information to determine whether the patient belongs to the owner / operator of the automated imaging terminal 200. For example, if the automated imaging terminal 200 is owned / operated by a physician or a service provider for a physician, the automated imaging terminal 200 may determine whether the patient has personal information or reference images on a file used by that physician or service provider.

[0030] This authentication can be facilitated through local storage 206a and / or remote database 206b, which can store patient information and / or reference images for the physician or service provider. Thus, patient information entered by the patient into the automated imaging terminal 200 can be simply compared with records stored in local storage 206a and / or remote database 206b to identify a match. Once a match is determined, the patient is alerted that they have been authenticated, the use of the automated imaging terminal 200 is unlocked, and the patient can continue to use the automated imaging terminal 200 to automatically capture OCT images.

[0031] If the corresponding patient information cannot be determined, the patient may be alerted and asked to contact their doctor, for example (to schedule an appointment). In some embodiments, the doctor may be suggested or automatically contacted by the automated imaging terminal 200. In some embodiments, the automated imaging terminal 200 may be used to collect reference images of the patient and then analyze them in real time (by local or remote service) to facilitate further imaging, or to send them to a doctor for further analysis. The automated imaging terminal 200 may also recommend or automatically suggest such a doctor and / or request doctor information from the patient.

[0032] Even if patient information and / or reference images are stored, additional information may be required to authenticate the patient. For example, a physician may perform periodic reviews of their patient files and indicate the suitability of reference images in relation to the stored patient information. For example, if it is determined that a reference image in the file is old, expired, of poor quality, or associated with another physician, the physician may indicate this along with the patient information. If such information exists, it may prevent the patient from being authenticated to use the automated imaging terminal 200, and the automated imaging terminal 200 may alert the patient to such problems, automatically contact a physician, or suggest a physician for the patient to contact.

[0033] In some embodiments, the owner / operator of the automated imaging terminal 200 provides access to the automated imaging terminal 200 as a service. For example, the owner / operator may provide this service to multiple physicians, where the automated imaging terminal 200 can provide the service to any of those physicians' patients. The automated imaging terminal 200 can obtain additional information 302 indicating whether the physicians are still subscribed to the owner / operator's service, and can authenticate patient use based on this information. In some embodiments, each patient subscribes to the service, thereby granting the patient access to the automated imaging terminal 200. Thus, authentication may be based on the patient's subscription.

[0034] The automated imaging terminal 200 can acquire an automated real-time image having a desired scan position 303 using the acquired reference image and other information 302. For example, using the exemplary method described in Figure 4, the automated imaging terminal 200 can acquire reference images 401 via a remote database 206b and save them to local storage 206a. The automated imaging terminal 200 can then acquire a real-time image 402 using the real-time imaging system 210. Referring to Figures 4 and 6, this method allows the automated imaging terminal 200 to acquire a real-time image 402 from the real-time imaging system 210. For example, a real-time image can be acquired from a fundus camera, an infrared video camera, scanning laser optometry images, frontal OCT images, etc.

[0035] To ensure proper imaging, the automated imaging terminal 200 can use a real-time imaging system 210 and a processor 204 to determine whether the patient's eyes are aligned within the viewport 211. In some embodiments, using machine learning techniques and the real-time imaging system 210, the processor 204 can detect the macula of each of the patient's eyes to determine whether the patient is centered within the viewport 211. If the patient is not centered within the viewport 211, the processor 204 can use an I / O device 208 to notify the patient to adjust through voice notifications, voice commands, or visual displays. LEDs or similar displays may be used to provide a visual indication of how to center the patient's eyes. For example, circles displayed on an LED display may indicate the desired position of the patient's eyes, and a second set of circles representing the real-time position of the patient's eyes may be provided to give the patient real-time feedback on how to adjust to the desired positioning. In other embodiments, a “point of aim” may be displayed to guide the patient to align themselves within the viewport 211. Other alignment techniques may be used, such as displaying a real-time video feed, a light indicating the center or focus of the imaging device, a ring of light, or audible feedback. The processor 204 can determine when the patient is correctly aligned using software that implements image processing and / or machine learning techniques.

[0036] The acquired real-time image 402 is then adjusted to register (403) a real-time image 603 and a reference image 601. Image registration 403 allows different datasets to be transformed into a single coordinate system, enabling the alignment of images taken at similar locations, the same patient at different times, and from different viewpoints. Image registration can be achieved in various ways, such as feature-based and intensity-based methods. In some embodiments, exemplary methods use feature-based registration techniques to identify the same anatomical structure 602 found in two spatially corresponding images (similar locations). Once the same structure is identified, the two images can be associated by the relative location of the anatomical structure 602.

[0037] As shown in Figure 6, the exemplary feature-based registration technique uses a reference image 601 having a desired scan location 604 and anatomical features 602, and a real-time image 603 including the scan center 608 and anatomical features 602. The exemplary method can associate the anatomical features 602 of the real-time image 603 with the anatomical features 602 of the reference image 601 using the feature-based registration technique 610. The anatomical features 602 may be various parts of the eye, such as the macula, optic nerve, blood vessels, etc.

[0038] Feature-based methods can establish relationships between multiple features or distinct points within an image to realize geometric transformations for mapping a real-time image 603 to a reference image 601. For example, a feature-based registration technique 610 may include various image transformations to align at least one orientation of the image, such as rotation, scaling, translation, and other affine transformations, so that the real-time image 603 can be mapped or fitted to the same coordinate system as the reference image 601. Other transformation methods, such as non-rigid transformations and multi-parameter transformations, may also be used. Transformations can be implemented using image processing and / or registration techniques and / or machine learning techniques. Such techniques may include, for example, feature-based alignment, model-fitting alignment, and pixel-based alignment.

[0039] By registering the real-time image 603 together with the reference image 601, a registered image 605 can be generated in which the real-time image 603 is mapped to the reference image 601, and the desired scan position 604 of the reference image 601 and the scan center 608 of the real-time image can be held within the registered image 605. That is, the registered image 605 contains the desired scan position 604 of the reference image 601 in relation to the scan center 608 of the real-time image 603. In some embodiments, the conversion can be performed directly on the real-time image, and therefore no additional registered image is generated.

[0040] The exemplary method then allows the registered image 404 to be transformed using transformation 612 to obtain the desired scan position 604 in the real-time image 603. In some embodiments, the inverse transformation of the transformation used in the registration process 610 is used to obtain the desired scan position 604 in the real-time image 603. For example, if the real-time image is rotated 45° clockwise during the registration process 610 to register the real-time image 603 on the reference image 601, then during the transformation of the registered image 605, transformation 612 may include rotating 45° counterclockwise, i.e., the inverse transformation of the transformation during the image registration process. Transformation process 404 includes only pixel information from the real-time image 603 while retaining the desired scan position 604 from the reference image 601. In other words, the registration transformation process transforms the desired scan position into the real-time image 603.

[0041] Once a desired scan position is associated with a real-time image, the coordinates or positional information of this desired scan position (for example, the center of the viewport 211 and the resulting image) can then be retrieved and / or stored for future use, for example, in local storage 206a or a remote database 206b.

[0042] Returning to Figure 3, the automated imaging terminal 200 can determine the acceptability of a real-time image based on a number of factors, such as proximity to the desired scan position, scan instructions, and noise level. For example, depending on the distance between the scan center 608 and the stored desired position 604, the viewport 211 and / or the real-time imaging system 210 may adjust the scan center 608 to move closer to the desired scan position 604. The real-time imaging system 210 can then acquire another real-time image of the new position and repeat the exemplary method described in Figure 4 until the scan center 608 of the real-time image falls within an acceptable proximity to the desired position 604. Referring to Figure 7, for example, the real-time image 700 with the desired position indicator 702 and scan center 706 stored may be determined to be acceptable because the desired position indicator 702 is within a predetermined proximity threshold 704 (e.g., a number of pixels or a determined distance).

[0043] The automated imaging terminal 200 can further indicate to the patient whether the real-time images acquired from the real-time imaging system 210 are acceptable, for example, by using an I / O device 208 for generating light, notifications, or voice commands generated on the automated imaging terminal 200, or by using similar actions. For example, if the patient is blinking (or otherwise having eye instability) and preventing the real-time imaging system 210 from capturing an acceptable image, the I / O device 208 can use a voice command to instruct the patient to keep their eyes open. The processor 204 can use image processing techniques and / or machine learning techniques to detect eye movements, instability, and / or blinking. For example, the processor can use image detection software to detect blinking indicated in real-time images with large dark bands or dark areas in fundus images or frontal images.

[0044] For example, referring to Figure 9, the real-time frontal image 904-2 has multiple black bands indicating the patient's blinking, whereas the real-time frontal image 904-1 does not have black bands and is registered in the reference fundus image 902. The processor 204 can also implement blink / instability / motion threshold tests to determine the appropriate time to acquire real-time or OCT images. For example, the processor 204 can detect that the patient has not blinked / is stable and / or is in the correct position for a given time before acquiring real-time or OCT images. For example, the patient has not blinked for several seconds and is correctly positioned in the viewport 211.

[0045] In some embodiments, an LED display visible from the viewport 211 can generate a focus for the patient to focus on during the imaging process. The LED display may be overlaid on the optical system of the viewport 211, allowing the patient to remain in front of the viewport 211 during the imaging process. The LED display may also generate flashing or lit lights to indicate different states of the process, such as a green light indicating that the image is acceptable, or a yellow light indicating that the image is not yet acceptable.

[0046] When the automated scan meets the acceptance (quality) criteria, the OCT imaging system 212 automatically acquires an OCT image 305 at the determined desired scan position. For example, if the real-time image 700 is determined to be acceptable, the automated imaging terminal 200 can then acquire an OCT image by adjusting (e.g., centering) the viewport 211 and / or the OCT imaging system 212 on the same scan center 706 as the real-time image 700. For example, as shown in Figure 8, the OCT imaging system 212 can automatically acquire 16 structural OCT B scans numbered #0 to #15, centered on the scan center 706 of the real-time image 700 or the desired scan position 702. The automated imaging terminal 200 can adjust the OCT imaging system as appropriate using actuators, motors, etc. In another embodiment, the automated imaging terminal 200 keeps the OCT imaging system 212 and the real-time imaging system 210 centered at the same position throughout the process. Therefore, when the automated real-time scan meets the desired threshold, the automated imaging terminal 200 is within position to acquire an OCT image.

[0047] The automated imaging terminal 200 can acquire OCT images 305 using various scan patterns and techniques, such as radial scans, circle scans, vertical scans, and horizontal scans. These scan patterns may be indicated by scan settings acquired using reference images and may be specific to or tailored to each patient. Therefore, if a particular scan method / pattern is desired by the physician or is more suitable for that particular patient or medical condition, that scan method / pattern can be automatically indicated and used by the automated imaging terminal 200.

[0048] Computer 202 can store acquired OCT images in local storage 206a or a remote database 206b. In some embodiments, computer 202 can store acquired OCT images in local storage 206a for later uploading to the remote database 206b. For example, if the internet connection is lost or interrupted during scanning, the automated imaging terminal 200 can terminate the scanning process, save the acquired OCT images locally, and upload the OCT images to the remote database after the internet connection is restored. Computer 202 can link the acquired OCT images to a patient using previously acquired patient information. In some embodiments, the OCT images are saved to a patient file on the remote database 206b and later reviewed by a physician. The physician can then modify the desired scan location in the reference image, or the instructions on the automated imaging terminal 200, if desired.

[0049] This allows for continuous review and feedback from a physician without the need to schedule appointments. The physician may also include instructions to be displayed to the patient on their next visit to the automated imaging terminal 200. For example, if the physician finds an abnormality, they can present the user with a reminder or notification to contact the physician for further evaluation. The reminder or notification may be displayed on the device via the viewport 211 or on an information LED display located on the automated imaging terminal 200. In some embodiments, the reminder or notification may be sent directly to the patient through other forms of communication, such as using the patient's mobile device.

[0050] Using the exemplary method described above, the automated imaging terminal 200 acquires OCT images 305 specific to each patient, since the method can rely on information specific to that patient. For example, a patient's reference image may be marked by a physician who has performed the patient's examination and knows details about the patient's medical condition. This information may be stored and / or associated with the patient's specific reference image and may be acquired and used by the automated imaging terminal 200.

[0051] While the above features are diverse, it should be understood that these features can be used individually or in any combination thereof. Furthermore, it should be understood that those skilled in the art in which the claimed example relates may conceive of variations and modifications.

Claims

1. Upon receiving input from the patient, Obtaining an existing reference image of the object from a remote database, which indicates the desired scan position, Retrieving personal information and / or scan settings relating to the patient from the remote database, wherein the personal information and / or scan settings are associated with the existing reference image specific to the patient. To acquire a real-time image of the aforementioned object, The real-time image is registered to the existing reference image, Based on the registration, the desired scan position on the real-time image is determined, The system automatically acquires an OCT image of the object at the desired scan position according to the acquired personal information and / or scan settings. A method that includes [a certain feature].

2. The aforementioned existing reference image was originally obtained by a physician, according to the method of claim 1.

3. The method according to claim 1, wherein the real-time image is an OCT frontal image.

4. Based on the input and personal information obtained from the patient, the patient is authenticated. The method according to claim 1, further comprising:

5. The method according to claim 1, wherein registering the real-time image and determining the desired scan position on the real-time image are performed by a machine learning system.

6. The method according to claim 1, wherein the OCT image at the desired scan position is automatically acquired based on whether the desired scan position is within a threshold range of the center of the real-time image.

7. Determining that the desired scan position is not within the threshold range of the center of the real-time image, To acquire a second real-time image of the aforementioned object, The second real-time image is registered to the reference image, Based on the registration of the second real-time image, the desired scan position on the second real-time image is determined, The method according to claim 6, comprising:

8. The method according to claim 1, wherein the scan settings include a patient-specific scan pattern, and the OCT image is automatically acquired according to the scan pattern.

9. Align the OCT imaging system according to the desired scan position. The method according to claim 1, further comprising:

10. The method according to claim 1, wherein the object is an eye.

11. A system including an optical coherence tomography (OCT) imaging system, A system comprising one or more processors, The aforementioned one or more processors, collectively, Upon receiving input from the patient, In response to input from the patient, the system retrieves an existing reference image of the object from a remote database, which indicates the desired scan position. From the remote database, retrieve personal information and / or scan settings relating to the patient, which are associated with the existing reference image unique to the patient. A real-time image of the aforementioned object is acquired, The aforementioned real-time image is registered as a reference image, Based on the registration, the desired scan position on the real-time image is determined. A system that, in accordance with the acquired personal information and / or scan settings, automatically acquires an OCT image of the object at the desired scan position using an OCT imaging system.

12. The aforementioned reference image was initially obtained by a physician, relating to the system according to claim 11.

13. The system according to claim 11, wherein the real-time image is an OCT frontal image acquired using the OCT imaging system.

14. The aforementioned one or more processors can be further collectively, The system according to claim 11, configured to authenticate the patient's use of the system based on the input from the patient and the acquired personal information.

15. The system according to claim 11, wherein the real-time image is registered in the reference image by one or more processors configured as a machine learning system.

16. The system according to claim 11, wherein the OCT image at the desired scan position is automatically acquired based on whether the desired scan position is within a threshold range of the center of the real-time image.

17. The aforementioned one or more processors are further collectively, It is determined that the desired scan position is not within the threshold range of the center of the real-time image. A second real-time image of the object is acquired. The second real-time image is registered to the reference image, The system according to claim 16, wherein the desired scan position on the second real-time image is determined based on the registration of the second real-time image.

18. The system according to claim 11, wherein the scan settings include a patient-specific scan pattern, and the OCT image is automatically acquired according to the scan pattern.

19. The aforementioned one or more processors are further collectively, The system according to claim 11, configured to align the OCT imaging system according to the desired scan position.

20. The system according to claim 11, wherein the object is an eye.

Images