Eye tracking method, device, and storage medium used in anterior segment OCTA

Abstract

The present disclosure provides an eye tracking method, device, apparatus, and storage medium for use in anterior segment OCTA. The eye tracking method for use in anterior segment OCTA includes acquiring two consecutive frames of pupil diagrams, extracting contours for each of the two frames of pupil diagrams to obtain two corresponding pupil contours, determining whether the two pupil contours are similar to a reference contour, and, in response to the two pupil contours being similar to the reference contour, calculating a center position shift of one of the two pupil contours relative to the other pupil contour.

Description

[Technical Field]

[0001] This application claims priority to a Chinese patent application bearing application number 202111489187.2, filed with the China Patent Office on December 7, 2021, the entire contents of which are incorporated herein by reference.

[0002] The present disclosure relates to the technical field of eye tracking, and to an eye tracking method, device, apparatus, and storage medium used, for example, in anterior segment Optical Coherence Tomography Angiography (OCTA). [Background technology]

[0003] OCTA is a new, non-invasive fundus imaging technique that was first applied to the posterior segment of the eye, i.e., the fundus. It can recognize retinal and choroidal blood flow dynamics with high resolution and capture images of retinal and choroidal microvascular circulation in living tissue. OCTA has unique advantages in detecting changes in normal retinal and choroidal blood vessels, as well as disease management, follow-up, and treatment efficacy. In the anterior segment, blood flow signals in the scanned area are obtained through signal changes in optical coherence tomography (OCT), which scans the same cross-section multiple times. By scanning multiple cross-sections consecutively, OCTA images of the scanned area in the anterior segment can be obtained.

[0004] Current OCTA is not suitable for all patients, and OCTA images can be inaccurate if the patient has poor fixation, frequent blinking, or eye movement. Summary of the Invention

[0005] The present disclosure provides an eye tracking method, device, equipment, and storage medium for use in anterior segment OCTA that can improve the problem that OCTA is not suitable for all patients, and that OCTA images can be inaccurate, especially when the patient has poor fixation, frequent blinking, or eye movement.

[0006] In a first aspect of the present disclosure, acquiring two consecutive frames of pupillograms; extracting a contour from each of the two frames of pupillary images to obtain two corresponding pupil contours; determining whether the two pupil contours are similar to a reference contour; and calculating a deviation in center position of one of the two pupil contours relative to the other pupil contour in response to the two pupil contours being similar to the reference contour.

[0007] In a second aspect of the present disclosure, an acquisition module configured to acquire two consecutive frames of pupillogram; an extraction module configured to extract a contour from each of the two frames of pupillary contours to obtain two corresponding pupillary contours; a determining module configured to determine whether the two pupil contours are similar to a reference contour; and a calculation module configured to calculate a deviation in center position of one of the two pupil contours relative to the other pupil contour in response to the two pupil contours being similar to a reference contour.

[0008] In a third aspect of the present disclosure, there is provided an electronic device, the electronic device including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement an eye tracking method for use in an anterior segment OCTA according to an embodiment of the present disclosure.

[0009] In a fourth aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program that, when executed by a processor, implements an eye tracking method for use in anterior segment OCTA as described in the embodiments of the present disclosure. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a normally captured pupil diagram according to an embodiment of the present disclosure. [Figure 2] FIG. 1 is a flow diagram of an eye tracking method used in anterior segment OCTA according to an embodiment of the present disclosure. [Figure 3] 1 is a schematic diagram of a pupil contour extraction process according to an embodiment of the present disclosure; [Figure 4] FIG. 10 is a schematic diagram showing dissimilarities between the pupil contour and the reference contour according to an embodiment of the present disclosure. [Figure 5] FIG. 10 is a schematic diagram showing the similarity between a pupil contour and a reference contour according to an embodiment of the present disclosure. [Figure 6] FIG. 1 is a structural schematic diagram of an eye tracking device used in an anterior segment OCTA according to an embodiment of the present disclosure. [Figure 7] 1 is a structural schematic diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, technical solutions in the embodiments of the present disclosure will be described with reference to the drawings in the embodiments of the present disclosure.

[0012] The eye tracking method used in the anterior segment OCTA according to the embodiments of the present disclosure is applicable to the field of eye tracking.

[0013] OCTA detects the movement of red blood cells in the vascular lumen by measuring changes in OCT signals obtained by multiple scans of the same cross-section, and then integrates the information from successive en face OCT images to obtain a complete 3D image of the retina and choroid. En face OCT is a transverse tomographic imaging technique that uses software processing to generate images based on conventional high-density B-scan images.

[0014] OCTA is not suitable for all patients. Only when the patient's visual acuity is good and the optic tract is transparent can OCTA images with good blood flow continuity and high-quality scanning signals be obtained. The time required for a single OCTA blood flow scan is determined by the scanning range and light source frequency. A large scanning range and high light source frequency requirements result in a long OCTA imaging time, which can lead to poor visual acuity, frequent blinking, and eye movement, resulting in poor OCTA scanning signal strength and poor image quality.

[0015] Therefore, the introduction of eye tracking is essential in the scanning process, as it can automatically measure the position of the patient's pupil, recognize and eliminate blinking and eye movement, and obtain high-quality pupil maps of the movement direction and magnitude between two consecutive positions, making subsequent OCTA imaging more accurate.

[0016] 1 is a normally photographed pupil diagram according to an embodiment of the present disclosure. Referring to FIG. 1, in the related art, a typical strategy for recognizing a pupil includes steps such as image filtering, image binarization, edge detection, and ellipse fitting. Meanwhile, when a person blinks, i.e., when a part or all of the pupil is obstructed by eyelids or eyelashes, the obstructed part is generally excluded, and only the valid area is used for ellipse fitting.

[0017] The ellipse fitting method involves first extracting a region of interest from an image using a mask, then binarizing the image using a histogram to obtain a threshold, then extracting a contour from the binarized image using an edge following algorithm, and finally fitting an ellipse to the extracted contour. If the error between the fitted ellipse and the original contour is greater than a threshold, a random consensus algorithm is used to discard outliers.

[0018] In the related art, many technical solutions require binarizing the image, but it is not easy to determine the threshold required for binarization. Once the image quality is poor or the threshold is not selected appropriately, the area marked by the binarized image may not necessarily be the pupil.

[0019] In addition, in many technical solutions, the position of the pupil is recognized by fitting an ellipse. However, this method has some drawbacks. For example, in an ophthalmic examination, the patient's pupil may already be deformed, and in this case, fitting it with a pre-defined shape (e.g., an ellipse) will lead to large errors. Moreover, fitting an ellipse itself will also lead to errors.

[0020] There are currently no eye tracking solutions specifically targeted at anterior segment OCTA, and customizing the solution would require additional recognition of whether the patient is blinking, something that most technology solutions fail to mention.

[0021] To solve the above technical problems, embodiments of the present disclosure provide an eye-tracking method for use in anterior segment OCTA, which in some embodiments can be performed by electronic devices.

[0022] 2 is a flow diagram of an eye tracking method used in an anterior segment OCTA according to an embodiment of the present disclosure. Referring to FIG. 2, the eye tracking method used in an anterior segment OCTA in this embodiment includes the following:

[0023] In operation 201, two consecutive frames of pupillograms are acquired.

[0024] In the embodiment of the present disclosure, the two consecutive frames of pupillary images are arbitrarily selected from normally captured pupillary images when performing OCTA image recognition on a patient. The two consecutive frames of pupillary images can be acquired using an optical diagnostic imaging device.

[0025] In the embodiments of the present disclosure, the number of image frames to be acquired is determined according to the resolution of the optical imaging device, and typically, the number of image frames to be acquired within one second is 30, 60, or 120. Within a certain period of time, the optical imaging device can acquire multiple image frames.

[0026] In an embodiment of the present disclosure, the device for performing diagnostic imaging based on optical principles includes an OCT imaging device and a pupil camera imaging device.

[0027] To facilitate the explanation of the eye tracking method used in the anterior segment OCTA, any one group of two consecutive frames of pupillary images from each group of multiple frame images will be selected as the two consecutive frames of pupillary images in a specific embodiment, and will be explained.

[0028] In an embodiment of the present disclosure, two consecutive frames of pupillograms are used for subsequent contour extraction to improve the accuracy of determining whether the patient is blinking or not.

[0029] In operation 202, contour extraction is performed on each of the two frames of pupillograms to obtain two corresponding pupil contours.

[0030] In the embodiment of the present disclosure, the contours of the pupils in the two frames of pupillogram are extracted using polar coordinate transformation and shortest path algorithm, and two pupil contours are obtained.

[0031] 3 is a schematic diagram of a pupil contour extraction process according to an embodiment of the present disclosure. Referring to FIG. 3, the method of extracting the contour from one of two frames of pupil diagrams involves performing polar coordinate transformation on a normally captured pupil diagram (a) to obtain a transformed pupil diagram (b), extracting the pupil boundary in the transformed pupil diagram (b) based on a shortest path algorithm to obtain a pupil diagram (c) from which the boundary has been extracted, and then performing an inverse polar coordinate transformation on the boundary in the pupil diagram (c) from which the boundary has been extracted to obtain a pupil diagram (d) including the pupil contour.

[0032] The pupil contour shown in pupil diagram (d) is a closed loop contour that surrounds the pupil and is a certain distance from the center of the image.

[0033] In the embodiment of the present disclosure, by using polar coordinate transformation and a shortest path algorithm to extract the contours of the pupils in the two frames of pupil diagrams, it is possible to avoid the problem that when using the image binarization method in the related art, the area marked in the binarized image may not necessarily be the pupil due to the difficulty in determining the threshold value required for binarization.

[0034] In some embodiments, performing contour extraction on a frame of pupillogram in operation 202 includes operations A1 to A3.

[0035] In operation A1, the pupillary diagram is subjected to polar coordinate transformation to obtain a transformed pupillary diagram.

[0036] In operation A2, the boundary of the pupil in the transformed pupillogram is extracted based on the shortest path algorithm.

[0037] In operation A3, the boundary is subjected to an inverse polar coordinate transformation to obtain the pupil contour.

[0038] In the embodiment of the present disclosure, the method for extracting a contour from one frame of pupillary image is described as follows.

[0039] In the embodiment of the present disclosure, polar coordinate transformation is used to detect closed contours in an image. Referring to Figure 3, a Cartesian coordinate system xoy is created in the pupil diagram, and the center (x0, y0) of the image is generally selected as the transformation center. Any point (x, y) on the plane of the Cartesian coordinate system xoy is centered at (x0, y0) and is corresponding to the polar coordinate (θ, r) in the polar coordinate system by the following calculation formula:

number

[0040] In an embodiment of the present disclosure, the pupil boundary in polar coordinates is found based on a shortest path algorithm, which includes depth- or breadth-first search algorithm, Floyd's algorithm, Dijkstra's algorithm, and Bellman-Ford algorithm.

[0041] In one embodiment, the Dijkstra algorithm is employed to find the boundary of the pupil in polar coordinates. The steps for employing the Dijkstra algorithm to find the boundary of the pupil in polar coordinates are as follows:

[0042] In operation 1, one array N and two sets P and Q are maintained in the transformed pupil diagram, where array N is used to store the shortest distance from the starting point to each vertex, set P is used to store points that have not been traversed, and set Q stores points that have already been traversed.

[0043] In operation 2, a starting point is selected from set P, added to set Q, and deleted from set P. The distances to points adjacent to the starting point are added to array N, and the distances to non-adjacent points are represented as infinity.

[0044] In operation 3, one point M closest to set Q (i.e., the point with the smallest edge weight value among all untraversed points connected to all already traversed points) is selected, and the point is added to set Q and deleted from set P.

[0045] In operation 4, a point C adjacent to point M is found, and it is determined whether the distance to reach point C stored in array N is smaller than the distance to reach point C from the starting point via M. If the distance to reach point C stored in array N is smaller than the distance to reach point C from the starting point via M, array N is updated, and if the distance to reach point C stored in array N is equal to or greater than the distance to reach point C from the starting point via M, a point adjacent to the next point M is searched for, and operation 4 is repeated until all adjacent points of point M have been traversed.

[0046] Until the set P to be traversed becomes empty, that is, the array N constitutes the boundary of the pupil in polar coordinates, the following steps are repeated: "select one point M closest to the set Q (i.e., the point with the smallest edge weight value among the untraversed points connected to all already traversed points), add that point to the set Q, and delete that point from the set P"; and "find a point C adjacent to the point M, and determine whether the distance to reach the point C stored in the array N is smaller than the distance to reach the point C from the starting point via M. If the distance to reach the point C stored in the array N is smaller than the distance to reach the point C from the starting point via M, update the array N; if the distance to reach the point C stored in the array N is equal to or greater than the distance to reach the point C from the starting point via M, continue to find a point adjacent to the next point M, and repeat operation 4 until all the adjacent points of the point M have been traversed."

[0047] This is the process of converting the transformed pupil diagram (b) in Figure 3 to the pupil diagram (c) after the boundary has been extracted.

[0048] In an embodiment of the present disclosure, the found pupil boundary is converted from polar coordinates to Cartesian coordinates and corresponds to the coordinates in the Cartesian coordinate system by the following calculation formula:

number

number

[0049] In operation 203, it is determined whether the two pupil contours are similar to the reference contour.

[0050] In an embodiment of the present disclosure, the reference contour is a pupil contour extracted from a pupil reference map, and the pupil reference map and the two consecutive frames of pupil maps to be acquired are taken of the same patient and for the same eye of the patient, and the pupil reference map is a normally taken pupil map in which the pupil of the same patient is not obstructed.

[0051] In the embodiment of the present disclosure, the similarity between the pupil contour and the reference contour is compared to determine the eye state and achieve better tracking. At the same time, the similarity comparison is not affected by the contour size, but only relates to the shape, so that the change in size of the pupil due to unevenness of the incident light, etc., can be ignored.

[0052] In some embodiments, the reference contour in operation 203 can be obtained by the following operations (operations B1 to B4).

[0053] In operation B1, a pupil reference map, which is a reference map in which the pupil is not obstructed, is obtained.

[0054] In operation B2, the pupil reference map is subjected to polar coordinate transformation to obtain a transformed pupil reference map.

[0055] In operation B3, the boundary of the pupil in the transformed pupil reference map is extracted based on the shortest path algorithm.

[0056] In operation B4, the boundary is subjected to an inverse polar coordinate transformation to obtain the reference contour of the pupil.

[0057] In the embodiment of the present disclosure, the operation of extracting the reference contour of the pupil reference diagram is the same as the process of extracting the contour for one frame of the pupil diagram in the above-mentioned operation 202. You can refer to operations A1 to A3 in operation 202, and the description will not be repeated here.

[0058] 4 is a schematic diagram showing dissimilar pupil contours and reference contours according to an embodiment of the present disclosure. Referring to FIG. 4, the reference contour in the pupil reference image (D) is dissimilar to either of the two pupil contours (d1) and (d2). In other words, when acquiring two consecutive frames of pupil images, the patient may blink or their eyelids or eyelashes may obstruct the pupil, i.e., the patient's pupil is obstructed.

[0059] 5 is a schematic diagram illustrating a pupil contour similar to a reference contour according to an embodiment of the present disclosure. Referring to FIG. 5, for one of the pupil diagrams (d3), the reference contour in the pupil reference diagram (D) is similar to the pupil contour in the pupil diagram (d3). In other words, when two consecutive frames of pupil diagrams are acquired, the patient does not blink, and the eyelids or eyelashes do not obstruct the pupil, i.e., the patient's pupil is not obstructed. If the distance between the reference contour in the pupil reference diagram (D) and the pupil contour in the pupil diagram is within a predetermined range, the pupil contour is deemed to be similar to the reference contour, and it can be determined that the patient's pupil was not obstructed when the pupil diagram was acquired.

[0060] In some embodiments, operation 203 includes operations C1 to C2.

[0061] In operation C1, the distance between the pupil contour and the reference contour is calculated.

[0062] In operation C2, it is determined whether the pupil contour is similar to the reference contour according to the preset distance range and distance (that is, the distance calculation result obtained by performing operation C1).

[0063] The distance between the disclosed pupil contour and the reference contour is the image moment (Hu moment). The Hu moment of an image is an image feature that is invariant to translation, rotation, and scale, and the calculation of the Hu moment includes the calculation of raw moments, central moments, and normalized central moments.

[0064] In one embodiment, the calculation of normalized central moment is adopted to calculate the distance between the pupil contour and the reference contour. The normalized central moment is a linear combination of normalized moments, which can still remain invariant even after operations such as image rotation, translation, scaling, etc., so we always use the normalized central moment to recognize image features.

[0065] Calculate the distance between the pupil contour and the reference contour using the following formula:

number

[0066] In an embodiment of the present disclosure, the distance between the pupil contour and the reference contour may be further calculated by the following formula:

number

[0067] In the embodiment of the present disclosure, the preset distance range is a manually defined distance range that can be set according to research needs. If the calculated distance is within the preset distance range, the pupil contour is similar to the reference contour.

[0068] In operation 204, in response to the two pupil contours being similar to the reference contour, a center position shift of one of the two pupil contours relative to the other pupil contour is calculated.

[0069] In an embodiment of the present disclosure, if it is determined that the two pupil contours in the pupil diagrams of two consecutive frames are both similar to the reference contour, i.e., if the pupil diagrams of the two consecutive frames are both normal, the deviation of the center position of one of these two pupil contours relative to the other pupil contour is calculated.

[0070] Calculate the deviation of the center position of one pupil contour relative to the other pupil contour using the following formula:

number

[0071] In some embodiments, operation 204 includes operations D1 to D2.

[0072] In operation D1, for each pupil contour, the center of mass of the pupil contour is obtained.

[0073] In operation D2, the deviation of the center position is calculated according to the two centers of mass.

[0074] In an embodiment of the present disclosure, the pupil center position is obtained by calculating the center of mass of the contour.

[0075] In an embodiment of the present disclosure, the pupil center position (i.e., the center of mass of the pupil contour) can be obtained by calculating the point in the contour. A ,y A ) is obtained by calculating the pupil center position using the following formula:

number

[0076] In the embodiments of the present disclosure, instead of using an ellipse fitting algorithm to fit the pupil center position, the pupil center position is directly calculated, thereby avoiding the error introduced by the ellipse fitting algorithm itself when using an ellipse fitting method, and avoiding the introduction of large errors caused by using a single preset shape (e.g., an ellipse) for fitting even if the patient's pupil may have already been deformed, and further avoiding the problem of inaccurate pupil marking caused thereby.

[0077] In an embodiment of the present disclosure, an overview of operations 201 to 204 is as follows.

[0078] The method for capturing pupillary images is a continuous capture method, in which one pupillary image is captured for each capture, i.e., the first pupillary image for any one of two consecutive frames of pupillary images in each group of the multiple frames. A contour is extracted from the first pupillary image, and the contour of the first pupillary image is compared with a reference contour for similarity. If the contour of the first pupillary image is similar to the reference contour, the capture continues, and a next pupillary image is captured, i.e., a second pupillary image for any one of two consecutive frames of pupillary images in each group of the multiple frames. A contour is extracted from the second pupillary image, and the contour of the second pupillary image is compared with the reference contour for similarity. If the pupil contours corresponding to these two pupillary images are both similar to the reference contour, the two pupillary images are confirmed to be valid, and the center offset of the two corresponding pupillary contours can be calculated.

[0079] In some embodiments, the method further comprises operation 205 .

[0080] In operation 205, in response to the two pupil contours not being similar to the reference contour, two consecutive frames of pupil images are reacquired, and the operations of “performing contour extraction on the two consecutive frames of pupil images respectively to obtain two corresponding pupil contours” and “determining whether the two pupil contours are similar to the reference contour” are performed, wherein the reacquired two consecutive frames of pupil images are images adjacent to the two consecutive frames of pupil images obtained in operation 201.

[0081] In the embodiment of the present disclosure, if the two pupil contours are not similar to the reference contour, it indicates that the patient blinks or that the eyelids or eyelashes are blocking the pupil, i.e., the patient's pupil is blocked. If the patient's pupil is blocked, the results obtained using the subsequent OCTA algorithm will also be inaccurate.

[0082] In an embodiment of the present disclosure, in order to obtain an accurate OCTA image, two consecutive frames of pupillary images adjacent to the two consecutive frames of pupillary images obtained in operation 201 are reacquired until an accurate OCTA image is obtained, and the following steps are performed: "contour extraction is performed for each of the two consecutive frames of pupillary images reacquired to obtain two corresponding pupil contours" and "determining whether these two pupil contours are similar to the reference contour."

[0083] In an embodiment of the present disclosure, each subsequent image taken should be run through the method to improve the accuracy of the OCTA image according to the needs of the study.

[0084] By adopting the above technical solutions, the eye tracking method used in the anterior segment OCTA according to the embodiment of the present disclosure acquires two consecutive frames of pupillary images, then extracts a contour for each of the two frames of pupillary images to obtain two corresponding pupillary contours, and then compares both of the two pupillary contours with a reference contour. If both of the two pupillary contours are similar to the reference contour, it is determined that the patient's pupil was not obstructed when the two frames of pupillary images were acquired. At this time, the deviation of the center position of one of the two pupillary contours relative to the other pupillary contour is calculated. By calculating the pupil image for subsequent use in the OCTA algorithm, a more accurate OCTA image can be obtained. This solves the problem that OCTA in the related art is not suitable for all patients, and in particular, when the patient has poor fixation, frequent blinking, or eye movement, the OCTA image becomes inaccurate. This improves the suitability of OCTA and eliminates the use of pupil images taken in situations where the patient has poor fixation, frequent blinking, or eye movement, thereby achieving the effect of improving the accuracy of OCTA images.

[0085] Although the above-described method embodiments have been described as a combination of a series of operations for ease of explanation, those skilled in the art should understand that the present disclosure is not limited to the order of operations described, as some operations may be performed in other orders or simultaneously based on the present disclosure. Furthermore, those skilled in the art should understand that the embodiments described in the specification are preferred embodiments, and that such operations and modules are not necessarily required for the present disclosure.

[0086] The above is an introduction to the method embodiment, and the following describes the proposals described in this disclosure through the device embodiment.

[0087] 6 is a structural schematic diagram of an eye tracking device used in an anterior segment OCTA according to an embodiment of the present disclosure. Referring to FIG. 6, the eye tracking device used in the anterior segment OCTA includes an acquisition module 601, an extraction module 602, a determination module 603, and a calculation module 604.

[0088] The acquisition module 601 is configured to acquire two consecutive frames of pupil diagrams, the extraction module 602 is configured to extract contours for each of the two frames of pupil diagrams to obtain two corresponding pupil contours, the determination module 603 is configured to determine whether or not the two pupil contours are similar to a reference contour, and the calculation module 604 is configured to calculate a deviation in center position of one of the two pupil contours relative to the other pupil contour in response to the two pupil contours being similar to the reference contour.

[0089] In some embodiments, the eye tracking device used in the anterior segment OCTA comprises: The image processing device further includes a reacquisition module 605 configured to, in response to these two pupil contours not being similar to the reference contour, reacquire two consecutive frames of pupil diagrams and perform the operations of "performing contour extraction for each of the reacquired two consecutive frames of pupil diagrams to obtain two corresponding pupil contours" and "determining whether these two pupil contours are similar to the reference contour", wherein these reacquired two consecutive frames of pupil diagrams are images adjacent to the previously acquired two consecutive frames of pupil contours.

[0090] For convenience and conciseness of description, the operation processes of the modules described above may refer to the corresponding processes in the method embodiments described above, and will not be described again here.

[0091] 7 is a structural schematic diagram of an electronic device according to an embodiment of the present disclosure. As shown in FIG. 7, the electronic device 700 shown in FIG. 7 includes a processor 701 and a memory 703. The processor 701 and the memory 703 are connected to each other. In one embodiment, the electronic device 700 may further include a transceiver 704. In practical applications, the number of transceivers 704 is not limited to one, and the structure of the electronic device 700 does not limit the embodiment of the present disclosure.

[0092] The processor 701 may be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof, which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with the teachings disclosed in this disclosure. The processor 701 may also be a combination that implements computing functions, including, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0093] The bus 702 may provide a path for transmitting information between the above components. The bus 702 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus 702 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus is represented by only one bold line in FIG. 7, but this does not indicate that there is only one bus or only one type of bus.

[0094] Memory 703 may be, but is not limited to, Read Only Memory (ROM) or other type of static storage device capable of storing static information and instructions, Random Access Memory (RAM) or other type of dynamic storage device capable of storing information and instructions, Electrically Erasable Programmable Read Only Memory (EEPROM), Compact Disc Read Only Memory (CD-ROM) or other optical disk storage, optical disk storage (including compressed optical disks, laser disks, optical disks, digital versatile optical disks, Blu-ray disks, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium accessible by a computer that can be configured to carry or store desired program code in the form of instructions or data structures.

[0095] The memory 703 is configured to store the code of an application that implements the ideas of the present disclosure and whose execution is controlled by the processor 701. The processor 701 is configured to execute the code of the application stored in the memory 703 to implement the contents of the method embodiments described above.

[0096] The electronic device 700 includes, but is not limited to, mobile terminals such as a mobile phone, a laptop computer, a digital broadcast receiver, a personal digital assistant (PDA), a tablet computer (Portable Android Device (PAD)), a portable multimedia player (Portable Media Player (PMP)), an in-car terminal (e.g., an in-car navigation terminal), etc., and fixed terminals such as a digital television (TV), a desktop computer, etc. The electronic device 700 shown in Fig. 7 is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present disclosure.

[0097] An embodiment of the present disclosure provides a computer-readable storage medium having stored thereon a computer program that, when run on a computer, enables the computer to perform corresponding content of the aforementioned method embodiments. Compared with the related art, in the embodiment of the present disclosure, two consecutive frames of pupillary images are acquired, and then contour extraction is performed on each of the two frames of pupillary images to obtain two corresponding pupillary contours. These two pupillary contours are then compared with a reference contour. If these two pupillary contours are similar to the reference contour, it is determined that the patient's pupil was not obstructed when these two frames of pupillary images were acquired. At this time, the center position deviation of one of the two pupillary contours relative to the other pupillary contour is calculated to be used in the subsequent OCTA algorithm, thereby obtaining a more accurate OCTA image. This solves the problem that OCTA in the related art is not suitable for all patients, and in particular, OCTA images are inaccurate when the patient has poor fixation, frequent blinking, or eye movement. This improves the suitability of OCTA and eliminates the use of pupil images acquired in situations where the patient has poor fixation, frequent blinking, or eye movement, thereby achieving the effect of improving the accuracy of OCTA images.

[0098] Although multiple steps in the flowcharts in the drawings are shown sequentially according to the direction of the arrows, these steps are not necessarily performed in the order shown by the arrows. Unless otherwise clearly stated herein, these steps are not limited to a strict order of execution and may be performed in other orders. Furthermore, at least some of the steps in the flowcharts in the drawings may include multiple substeps or multiple stages, and these substeps or stages may not necessarily be completed at the same time but may be performed at different times, and the order of execution may not necessarily be sequential, and may be alternated or performed with other steps or at least some of the substeps or stages of other steps.

Claims

1. Acquiring two consecutive frames of pupillograms of the eye to be examined; extracting a contour from each of the two frames of pupillary images to obtain two corresponding pupil contours; determining whether the two pupil contours are similar to a reference contour obtained by extracting the contour from a pupil reference image captured when the pupil of the eye to be tested is unobstructed; and calculating a center position shift of one of the two pupil contours relative to the other pupil contour in response to the two pupil contours being similar to the reference contour, for use in anterior segment OCTA of the eye to be tested. Eye tracking method applicable to anterior segment optical coherence tomography angiography (OCTA).

2. Extracting the contour of a pupillary image in one frame involves the following steps: performing a polar coordinate transformation on the pupillary map to obtain a transformed pupillary map; extracting a pupil boundary in the transformed pupillogram based on a shortest path algorithm; performing an inverse polar coordinate transformation on the boundary to obtain a corresponding pupil contour. The method of claim 1.

3. Determining whether a pupil contour is similar to the reference contour includes: calculating a distance between the pupil contour and the reference contour; determining whether the pupil contour is similar to the reference contour according to a preset distance range and the distance; The method of claim 1.

4. The calculation of the deviation of the center position of one pupil contour from the other pupil contour of the two pupil contours includes: responsive to each pupil contour, obtaining a center of mass of the pupil contour; and calculating the deviation of the center position according to the two centers of mass. The method of claim 1.

5. further comprising: in response to the two pupil contours being dissimilar to the reference contour, reacquiring two successive frames of pupil diagrams that are images adjacent to the two successive frames of pupil diagrams, extracting contours for each of the two successive frames of pupil diagrams to obtain two corresponding pupil contours, and determining whether the two pupil contours are similar to the reference contour. The method of claim 1.

6. The reference contour is An operation of obtaining the pupil reference map; performing polar coordinate transformation on the pupil reference diagram to obtain a transformed pupil reference diagram; extracting a pupil boundary in the transformed pupil reference map based on a shortest path algorithm; and performing an inverse polar coordinate transformation on the boundary to obtain a reference pupil contour. The method of claim 1.

7. An acquisition module configured to acquire two consecutive frames of pupillograms of the eye to be examined; an extraction module configured to extract a contour from each of the two frames of pupillary contours to obtain two corresponding pupillary contours; a determining module configured to determine whether the two pupil contours are similar to a reference contour obtained by extracting the contours from a pupil reference map captured when the pupil of the eye to be tested is not obstructed; a calculation module configured to calculate a center position shift of one of the two pupil contours relative to the other pupil contour in response to the two pupil contours being similar to the reference contour, for use in anterior segment OCTA of the eye to be tested; An eye tracking device that can be used for anterior segment optical coherence tomography angiography (OCTA).

8. and a reacquisition module configured to, in response to the two pupil contours not being similar to a reference contour, perform an operation of reacquiring two consecutive frames of pupil diagrams that are images adjacent to the two consecutive frames of pupil diagrams, extracting contours for each of the two consecutive frames of pupil diagrams, to obtain two corresponding pupil contours, and determining whether the two pupil contours are similar to the reference contour.

8. The apparatus of claim 7.

9. The present invention provides an eye tracking method that can be used for anterior segment optical coherence tomography angiography (OCTA) according to any one of claims 1 to 6, comprising a memory in which a computer program is stored and a processor, and when the processor executes the computer program, the eye tracking method can be used for anterior segment optical coherence tomography angiography (OCTA) according to any one of claims 1 to 6. electronic equipment.

10. A computer program is stored in the computer, which, when executed by a processor, realizes the eye tracking method usable for anterior segment optical coherence tomography angiography (OCTA) according to any one of claims 1 to 6. A computer-readable storage medium.

Images