Method and device for measuring human eye parameters of cornea cross-sectional image based on OCT (optical coherence tomography)

Abstract

The invention relates to the technical field of image processing, and discloses an OCT-based human eye parameter measurement method and device for corneal cross-sectional images, and the method comprises the steps: carrying out the scanning of human eyes based on OCT equipment, and obtaining the OCT image information of the human eyes; based on a preset segmentation algorithm, determining position information of a plurality of segmentation lines of the OCT image information according to the OCT image information; determining related position information of multiple human eyes according to the position information of all the segmentation lines; analyzing a first type of human eye parameters of the human eyes according to all the human eye related position information; based on a preset image processing algorithm, processing the OCT image to measure a second type of human eye parameters of the human eyes; and determining the first type of human eye parameters and the second type of human eye parameters as human eye parameter measurement results through the OCT equipment. Therefore, the accuracy and the richness degree of the measured human eye biological parameters can be improved, and the utilization rate of OCT equipment can be improved through the human eye biological parameters as many as possible.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method and device for measuring human eye parameters based on OCT corneal tomographic images. Background Art

[0002] Optical coherence tomography (OCT) is a non-invasive optical imaging technology. By scanning the reflected light at different depths, OCT can generate high-resolution tissue tomographic images. The existing ophthalmic imaging system based on OCT equipment mainly includes a light source module with a swept laser, a main interferometer module, a reference arm, a sample arm suitable for fundus mode, a control circuit module and an acquisition control and analysis system.

[0003] However, practice has found that the existing ophthalmic imaging systems based on OCT devices can usually only obtain the anterior segment and fundus retinal tomographic structure images, and the measured biological parameters of the human eye are usually only one or a few of many parameters such as axial length, corneal center thickness, anterior chamber depth, lens thickness, etc., which are not rich enough and the utilization rate of OCT devices is poor. It can be seen that it is particularly important to provide a new solution for measuring human eye parameters based on tomographic images generated by OCT devices to improve the richness of measuring human eye biological parameters. Summary of the invention The present invention provides a method and device for measuring human eye parameters based on OCT corneal tomographic images, which can improve the richness of measured human eye biological parameters and help improve the utilization rate of OCT equipment by measuring as many human eye biological parameters as possible.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for measuring human eye parameters based on corneal tomographic images using OCT, the method comprising: Scanning a human eye based on an OCT device to obtain OCT image information of the human eye, wherein the OCT image information includes a brightness value and / or a grayscale value of the OCT image; Based on a preset segmentation algorithm, according to the OCT image information, determine the position information of each of the plurality of segmentation lines of the OCT image information, wherein the segmentation lines are used to segment the OCT image into a plurality of tomographic images, wherein the tomographic images at least include a corneal tomographic image; Determine a plurality of human eye-related position information according to the position information of all the segmentation lines, each of the human eye-related position information includes one of corneal position information, retinal position information, iris and lens position information, and choroid position information; Analyzing first-category human eye parameters of the human eye according to all the human eye-related position information; Based on a preset image processing algorithm, the OCT image is processed to measure a second type of human eye parameter of the human eye, wherein the second type of human eye parameter includes a white-to-white parameter and a pupil diameter parameter; The first type of human eye parameters and the second type of human eye parameters are determined as parameter measurement results of the human eye by the OCT device.

[0005] As an optional embodiment, in the first aspect of the present invention, the first type of human eye parameters includes one or more combinations of axial length, central corneal thickness, retinal thickness, anterior chamber depth, lens thickness, vitreous cavity length and choroidal thickness; And, analyzing the first type of human eye parameters of the human eye according to all the human eye related position information includes: According to all the sub-position information included in all the human eye-related position information, determining from all the sub-position information the characteristic position information required for measuring the human eye-related parameters and the parameter type that can be measured by the characteristic position information; According to the parameter types corresponding to all the characteristic position information, all the characteristic position information are grouped to obtain a plurality of characteristic position information groups, each of the characteristic position information groups corresponds to a parameter type, and each of the characteristic position information groups includes at least one characteristic position information; Processing all the feature position information in each of the feature position information groups to obtain human eye parameters of a parameter type corresponding to the feature position information group; Determine human eye parameters of parameter types corresponding to all the feature position information groups as first-category human eye parameters.

[0006] As an optional implementation manner, in the first aspect of the present invention, each of the characteristic position information groups specifically includes: The corneal position information includes the highest point position of the corneal surface and the retinal surface position included in the retinal position information; or, The position information of the upper surface of the cornea included in the corneal position information and the position information of the lower surface of the cornea included in the corneal position information; or, The position information of the retinal nerve fiber layer included in the retinal position information and the position information of the extrinsic layer included in the retinal position information; or The cornea position information includes the position information of the cornea vertex and the iris and lens position information includes the position information of the front surface of the lens; or, The vertex position information of the front surface of the lens included in the iris and lens position information and the vertex position information of the back surface of the lens included in the iris and lens position information; or, The retinal position information includes the position information of the retinal pigment epithelium and the position information of the choroidal junction.

[0007] As an optional implementation, in the first aspect of the present invention, the processing of the OCT image based on a preset image processing algorithm to measure the second type of human eye parameter of the human eye includes: Projecting and synthesizing the OCT image to obtain a circular ring image corresponding to the OCT image, and preprocessing the circular ring image to obtain a target circular ring image, wherein the preprocessing includes smoothing or edge modification; and searching the target circular ring image for the longest distance of the eyeball boundary of the human eye in the target circular ring image in the horizontal direction according to the target circular ring image to obtain the white-to-white parameter; The OCT image is deformed and corrected to obtain a corrected OCT image; and the pupil diameter parameter of the human eye is measured according to the corrected OCT image.

[0008] As an optional implementation, in the first aspect of the present invention, projecting and synthesizing the OCT image to obtain a circular ring image corresponding to the OCT image includes: Based on the Canny edge detection algorithm, rectangle detection is performed on the OCT image to obtain rectangular feature data of the OCT image; Based on Hough transform or contour detection algorithm, detecting and extracting boundary information of the rectangular feature data, wherein the boundary information includes rectangle position information and / or rectangle size information; Calculate the annular region parameters corresponding to the rectangular feature data according to the rectangular position information and the rectangular size information, wherein the annular region parameters include one or more combinations of the inner diameter of the annular region, the outer diameter of the annular region and the center position of the annular region; Based on perspective transformation or affine transformation, according to the annular area parameters, the shape of the rectangle corresponding to the rectangular feature data is transformed to make the rectangle into a circular ring, and the circular ring is updated to the OCT image to replace the rectangle, so as to obtain a circular ring image corresponding to the OCT image.

[0009] As an optional implementation, in the first aspect of the present invention, the segmentation algorithm includes a shortest path Dijkstra algorithm; And, determining the position information of each of the plurality of segmentation lines of the OCT image information based on the preset segmentation algorithm according to the OCT image information includes: The brightness value or grayscale value included in the OCT image information is used as a pixel value to calculate a weight map; the weight map is flattened to obtain a flattened image, wherein the flattened image includes a plurality of target layers; Based on the shortest path Dijkstra algorithm, the starting point or the center point of each target layer is determined as a source node, and the remaining nodes except the source node are selected from the source node and the contour of the target layer, the path length between the source node and each of the remaining nodes is calculated, and the target node whose path length is the shortest path length is selected from all the remaining nodes; the line segment between the source node and the target node is determined as the dividing line of the target layer; the position information of the dividing line of the target layer is determined according to the position of the source node and the position of the target node in the flattened image; Wherein, all segmentation lines of the OCT image information include segmentation lines of all target layers.

[0010] As an optional embodiment, in the first aspect of the present invention, the method further comprises: Obtaining a first dividing line with the lowest steepness value and a second dividing line with the highest steepness value from all the dividing lines; According to the first dividing line and the second dividing line, fitting the points of the first dividing line and the points of the second dividing line into a circular image to calculate the radius parameter of the circular image; Based on a preset curvature radius calculation formula and according to the radius parameter, the corneal curvature radius of the human eye is calculated, and the corneal curvature radius is added to the parameter measurement result of the human eye.

[0011] The second aspect of the present invention discloses a device for measuring human eye parameters based on corneal tomographic images using OCT, the device comprising: A scanning module, used to scan a human eye based on an OCT device to obtain OCT image information of the human eye, wherein the OCT image information includes a brightness value and / or a grayscale value of the OCT image; A determination module, configured to determine, based on a preset segmentation algorithm and according to the OCT image information, position information of each of a plurality of segmentation lines of the OCT image information, wherein the segmentation lines are used to segment the OCT image into a plurality of tomographic images, wherein the tomographic images at least include a corneal tomographic image; The determination module is further used to determine a plurality of human eye-related position information according to the position information of all the segmentation lines, each of the human eye-related position information includes one of corneal position information, retinal position information, iris and lens position information, and choroid position information; An analysis module, used for analyzing a first type of human eye parameter of the human eye according to all the human eye related position information; a processing module, configured to process the OCT image based on a preset image processing algorithm to measure a second type of human eye parameter of the human eye, wherein the second type of human eye parameter includes a white-to-white parameter and a pupil diameter parameter; The determination module is further used to determine the first type of human eye parameters and the second type of human eye parameters as parameter measurement results of the human eye through the OCT device.

[0012] As an optional embodiment, in the second aspect of the present invention, the first type of human eye parameters includes one or more combinations of axial length, central corneal thickness, retinal thickness, anterior chamber depth, lens thickness, vitreous cavity length and choroidal thickness; And, the analysis module analyzes the first type of human eye parameters of the human eye according to all the human eye related position information specifically including: According to all the sub-position information included in all the human eye-related position information, determining from all the sub-position information the characteristic position information required for measuring the human eye-related parameters and the parameter type that can be measured by the characteristic position information; According to the parameter types corresponding to all the characteristic position information, all the characteristic position information are grouped to obtain a plurality of characteristic position information groups, each of the characteristic position information groups corresponds to a parameter type, and each of the characteristic position information groups includes at least one characteristic position information; Processing all the feature position information in each of the feature position information groups to obtain human eye parameters of a parameter type corresponding to the feature position information group; Determine human eye parameters of parameter types corresponding to all the feature position information groups as first-category human eye parameters.

[0013] As an optional implementation manner, in the second aspect of the present invention, each of the characteristic position information groups specifically includes: The corneal position information includes the highest point position of the corneal surface and the retinal surface position included in the retinal position information; or, The position information of the upper surface of the cornea included in the corneal position information and the position information of the lower surface of the cornea included in the corneal position information; or, The position information of the retinal nerve fiber layer included in the retinal position information and the position information of the extrinsic layer included in the retinal position information; or The cornea position information includes the position information of the cornea vertex and the iris and lens position information includes the position information of the front surface of the lens; or, The vertex position information of the front surface of the lens included in the iris and lens position information and the vertex position information of the back surface of the lens included in the iris and lens position information; or, The retinal position information includes the position information of the retinal pigment epithelium and the position information of the choroidal junction.

[0014] As an optional implementation, in the second aspect of the present invention, the processing module processes the OCT image based on a preset image processing algorithm to measure the second type of human eye parameter of the human eye specifically includes: Projecting and synthesizing the OCT image to obtain a circular ring image corresponding to the OCT image, and preprocessing the circular ring image to obtain a target circular ring image, wherein the preprocessing includes smoothing or edge modification; and searching the target circular ring image for the longest distance of the eyeball boundary of the human eye in the target circular ring image in the horizontal direction according to the target circular ring image to obtain the white-to-white parameter; The OCT image is deformed and corrected to obtain a corrected OCT image; and the pupil diameter parameter of the human eye is measured according to the corrected OCT image.

[0015] As an optional implementation, in the second aspect of the present invention, the processing module projects and synthesizes the OCT image to obtain a circular ring image corresponding to the OCT image, which specifically includes: Based on the Canny edge detection algorithm, rectangle detection is performed on the OCT image to obtain rectangular feature data of the OCT image; Based on Hough transform or contour detection algorithm, detecting and extracting boundary information of the rectangular feature data, wherein the boundary information includes rectangle position information and / or rectangle size information; Calculate the annular region parameters corresponding to the rectangular feature data according to the rectangular position information and the rectangular size information, wherein the annular region parameters include one or more combinations of the inner diameter of the annular region, the outer diameter of the annular region and the center position of the annular region; Based on perspective transformation or affine transformation, according to the annular area parameters, the shape of the rectangle corresponding to the rectangular feature data is transformed to make the rectangle into a circular ring, and the circular ring is updated to the OCT image to replace the rectangle, so as to obtain a circular ring image corresponding to the OCT image.

[0016] As an optional implementation, in the second aspect of the present invention, the segmentation algorithm includes a shortest path Dijkstra algorithm; And, the determination module determines the position information of each of the plurality of segmentation lines of the OCT image information based on the preset segmentation algorithm and according to the OCT image information, specifically including: The brightness value or grayscale value included in the OCT image information is used as a pixel value to calculate a weight map; the weight map is flattened to obtain a flattened image, wherein the flattened image includes a plurality of target layers; Based on the shortest path Dijkstra algorithm, the starting point or the center point of each target layer is determined as a source node, and the remaining nodes except the source node are selected from the source node and the contour of the target layer, the path length between the source node and each of the remaining nodes is calculated, and the target node whose path length is the shortest path length is selected from all the remaining nodes; the line segment between the source node and the target node is determined as the dividing line of the target layer; the position information of the dividing line of the target layer is determined according to the position of the source node and the position of the target node in the flattened image; Wherein, all segmentation lines of the OCT image information include segmentation lines of all target layers.

[0017] As an optional implementation, in the second aspect of the present invention, the device further includes: An acquisition module, used for acquiring a first segmentation line with the lowest steepness value and a second segmentation line with the highest steepness value from all the segmentation lines; A fitting module, used for fitting points of the first dividing line and points of the second dividing line into a circular image according to the first dividing line and the second dividing line, so as to calculate a radius parameter of the circular image; A calculation module is used to calculate the corneal curvature radius of the human eye based on a preset curvature radius calculation formula and according to the radius parameter, and add the corneal curvature radius to the parameter measurement result of the human eye.

[0018] The third aspect of the present invention discloses another device for measuring human eye parameters based on corneal tomographic images using OCT, the device comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for measuring human eye parameters based on OCT corneal tomographic images disclosed in the first aspect of the present invention.

[0019] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the human eye parameter measurement method based on OCT corneal tomographic images disclosed in the first aspect of the present invention.

[0020] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: In an embodiment of the present invention, a human eye is scanned based on an OCT device to obtain OCT image information of the human eye, where the OCT image information includes a brightness value and / or a grayscale value of the OCT image; based on a preset segmentation algorithm, according to the OCT image information, the position information of each of a plurality of segmentation lines of the OCT image information is determined, the segmentation lines are used to segment the OCT image into a plurality of tomographic images, and the tomographic images at least include a corneal tomographic image; based on the position information of all segmentation lines, a plurality of human eye-related position information is determined, where each human eye-related position information includes one of corneal position information, retinal position information, iris and lens position information, and choroid position information; based on all the human eye-related position information, a first type of human eye parameter of the human eye is analyzed; based on a preset image processing algorithm, the OCT image is processed to measure a second type of human eye parameter of the human eye, where the second type of human eye parameter includes a white-to-white parameter and a pupil diameter parameter; the first type of human eye parameter and the second type of human eye parameter are determined as the parameter measurement result of the human eye by the OCT device. It can be seen that the implementation of the present invention can scan the human eye based on the OCT device to obtain the OCT image information of the human eye; and based on the preset segmentation algorithm, according to the OCT image information, accurately determine the position information of each of the multiple segmentation lines of the OCT image information, and determine multiple human eye-related position information based on the position information of all the segmentation lines, and can improve the accuracy and efficiency of determining the human eye-related position information in the OCT image based on the segmentation algorithm, analyze the first type of human eye parameters based on all the human eye-related position information, and can improve the measurement accuracy and efficiency of the first type of human eye parameters based on the human eye-related position information; And based on a preset image processing algorithm, the OCT image is processed to measure a second type of human eye parameter of the human eye, which can improve the measurement accuracy and efficiency of the second type of human eye parameter based on the image processing algorithm; then the first type of human eye parameter and the second type of human eye parameter are determined as the parameter measurement result of the human eye through the OCT device, and the accuracy and richness of the measured human eye biological parameters can be improved by providing a variety of human eye parameter measurement methods, and the utilization rate of the OCT device can be improved by measuring as many human eye biological parameters as possible, which is also beneficial to improving the subsequent analysis efficiency and analysis accuracy of the human eye biological parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 It is a flow chart of a method for measuring human eye parameters based on OCT corneal tomographic images disclosed in an embodiment of the present invention; Figure 2 is a schematic diagram of a corneal tomographic image based on an OCT device disclosed in an embodiment of the present invention; Figure 3 is a schematic diagram of a lens tomographic image based on an OCT device disclosed in an embodiment of the present invention; Figure 4 is a schematic diagram of a retinal tomographic image based on an OCT device disclosed in an embodiment of the present invention; Figure 5 It is a flow chart of another method for measuring human eye parameters based on OCT corneal tomographic images disclosed in an embodiment of the present invention; Figure 6 is a schematic diagram of a pupil diameter-related image before correction disclosed in an embodiment of the present invention; Figure 7 is a schematic diagram of a corrected pupil diameter-related image disclosed in an embodiment of the present invention; Figure 8 It is a schematic structural diagram of a human eye parameter measurement device based on OCT corneal tomographic images disclosed in an embodiment of the present invention; Fig. 9 It is a structural schematic diagram of another device for measuring human eye parameters based on OCT corneal tomographic images disclosed in an embodiment of the present invention; Fig.10 It is a structural schematic diagram of another device for measuring human eye parameters based on OCT corneal tomographic images disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0025] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0026] The present invention discloses a method and device for measuring human eye parameters based on OCT corneal tomographic images. The method and device can scan a human eye based on an OCT device to obtain OCT image information of the human eye. The method and device can accurately determine the position information of each of a plurality of segmentation lines of the OCT image information based on the OCT image information based on a preset segmentation algorithm, determine a plurality of human eye-related position information based on the position information of all the segmentation lines, improve the accuracy and efficiency of determining the human eye-related position information in the OCT image based on the segmentation algorithm, analyze the first type of human eye parameters based on all the human eye-related position information, and improve the first type of human eye parameters based on the human eye-related position information. The method can improve the measurement accuracy and efficiency of eye parameters; and based on a preset image processing algorithm, process the OCT image to measure the second type of human eye parameters of the human eye, which can improve the measurement accuracy and efficiency of the second type of human eye parameters based on the image processing algorithm; and then determine the first type of human eye parameters and the second type of human eye parameters as the parameter measurement results of the human eye through the OCT device, and by providing a variety of human eye parameter measurement methods, it can improve the accuracy and richness of the measured human eye biological parameters, and can improve the utilization rate of the OCT device by measuring as many human eye biological parameters as possible, which is also conducive to improving the subsequent analysis efficiency and accuracy of the human eye biological parameters. The following are detailed descriptions.

[0027] Embodiment 1 See also Figure 1 , Figure 1 1 is a flow chart of a method for measuring human eye parameters based on OCT corneal tomographic images disclosed in an embodiment of the present invention. Figure 1The described method for measuring human eye parameters based on corneal tomographic images of OCT can be applied to a human eye parameter measuring device based on corneal tomographic images of OCT, wherein the device may include a measuring device or a measuring server, wherein the measuring server may include a cloud server or a local server, which is not limited in the embodiments of the present invention. Figure 1 As shown, the method for measuring human eye parameters based on OCT corneal tomographic images may include the following operations: 101. Scan the human eye based on the OCT device to obtain OCT image information of the human eye.

[0028] In the embodiment of the present invention, the OCT image information may include a brightness value and / or a grayscale value of the OCT image.

[0029] 102. Based on a preset segmentation algorithm and according to the OCT image information, determine position information of each segmentation line of the OCT image information.

[0030] In the embodiment of the present invention, the segmentation algorithm may be a shortest path algorithm or other algorithms that can achieve the same segmentation purpose, wherein the shortest path algorithm is to obtain the specific position of the segmentation line by traversing and calculating the brightness value / grayscale value on the OCT image. The segmentation line can be used to segment the OCT image into multiple tomographic images. Optionally, the tomographic image includes at least a corneal tomographic image, and may also include at least one of a retinal tomographic image, an iris tomographic image, a lens tomographic image, and a choroidal tomographic image, which is not limited in the embodiment of the present invention. For example, Figure 2-4 As shown, Figure 2 is a schematic diagram of a corneal tomographic image based on an OCT device disclosed in an embodiment of the present invention, Figure 3 is a schematic diagram of a lens tomographic image based on an OCT device disclosed in an embodiment of the present invention, Figure 4 It is a schematic diagram of a retinal tomographic image based on an OCT device disclosed in an embodiment of the present invention.

[0031] 103. Determine multiple eye-related position information based on the position information of all segmentation lines.

[0032] In an embodiment of the present invention, optionally, each person's eye-related position information may include one of corneal position information, retinal position information, iris and lens position information, and choroid position information. Among them, the corneal position information may include at least one of the position information of the upper surface of the cornea, the position information of the lower surface of the cornea, the position information of the anterior surface of the cornea, and the position information of the posterior surface of the cornea. The retinal position information may include at least one of the position information of the retinal nerve fiber layer (RNFL), the position information of the outer lamina (OPL), the position information of the inner limiting membrane of the retina, and the position information of the retinal pigment epithelium (RPE) layer. The iris and lens position information may include at least one of the iris position information, the position information of the anterior surface of the lens, the position information of the posterior surface of the lens, and the position information of the posterior capsule of the lens. The choroid position information may include the position information of the choroid / sclera junction, which is not limited in the embodiment of the present invention.

[0033] 104. Analyze the first type of human eye parameters based on all the relevant position information of the human eye.

[0034] In an embodiment of the present invention, optionally, the first type of human eye parameters may include one or more combinations of axial length (Axial length, AXL), central corneal thickness (CCT), retinal thickness (Retinalthickness, RT), anterior chamber depth (Anterior chamber depth), lens thickness (Lens thickness, LT), vitreous cavity length (Vitreous thickness, VT) and choroidal thickness (choroidal thickness, CT), which is not limited in the embodiment of the present invention.

[0035] 105. Based on a preset image processing algorithm, the OCT image is processed to measure the second type of human eye parameters of the human eye.

[0036] In the embodiment of the present invention, the second type of human eye parameters may include a white to white parameter (WTW) and a pupil diameter parameter (PD).

[0037] In the embodiment of the present invention, there is no order of precedence between step 105 and steps 102 to 104, that is, step 105 may occur before steps 102 to 104, or after steps 102 to 104, or may occur simultaneously with steps 102 to 104, which is not limited in the embodiment of the present invention.

[0038] 106. Determine a first type of human eye parameter and a second type of human eye parameter as a parameter measurement result of the human eye using an OCT device.

[0039] In an embodiment of the present invention, optionally, the measured biological parameters of the human eye can be used as a basis for subsequent analysis of the cause of the human eye disease, and can also be used as a basis for generating a treatment strategy for the cause of the human eye disease, which is not limited in the embodiment of the present invention.

[0040] It can be seen that implementation Figure 1 The described method for measuring human eye parameters based on OCT corneal tomographic images can scan the human eye based on the OCT device to obtain OCT image information of the human eye; and based on a preset segmentation algorithm, accurately determine the position information of each of the multiple segmentation lines of the OCT image information according to the OCT image information, determine multiple human eye-related position information according to the position information of all the segmentation lines, and can improve the accuracy and efficiency of determining the human eye-related position information in the OCT image based on the segmentation algorithm, analyze the first type of human eye parameters based on all the human eye-related position information, and can improve the first type of human eye parameters based on the human eye-related position information. Measurement accuracy and efficiency; and based on a preset image processing algorithm, processing the OCT image to measure the second type of human eye parameters of the human eye, which can improve the measurement accuracy and efficiency of the second type of human eye parameters based on the image processing algorithm; and then determining the first type of human eye parameters and the second type of human eye parameters as the parameter measurement results of the human eye through the OCT device, by providing a variety of human eye parameter measurement methods can improve the accuracy and richness of the measured human eye biological parameters, can improve the utilization rate of the OCT device by measuring as many human eye biological parameters as possible, but also conducive to improving the subsequent analysis efficiency and analysis accuracy of the human eye biological parameters.

[0041] In an optional embodiment, the above step 104 of analyzing the first type of human eye parameters according to all human eye-related position information may include: According to all the sub-position information included in all the eye-related position information, determining from all the sub-position information the characteristic position information required for measuring the human eye-related parameters and the parameter type that can be measured by the characteristic position information; According to the parameter types corresponding to all the characteristic position information, all the characteristic position information are grouped to obtain a plurality of characteristic position information groups, each characteristic position information group corresponds to a parameter type, and each characteristic position information group includes at least one characteristic position information; Processing all feature position information in each feature position information group to obtain human eye parameters of parameter types corresponding to the feature position information group; The human eye parameters of the parameter types corresponding to all the feature position information groups are determined as the first type of human eye parameters.

[0042] Exemplarily, taking corneal position information as an example, all relevant position information of the cornea includes position information of the upper and lower surfaces of the cornea, position information of the front and back surfaces, and position information of intersections with other tomographic images. The position information of the upper and lower surfaces of the cornea and the position information of the front and back surfaces are determined as characteristic position information for measuring human eye-related parameters. At this time, the types of parameters that can be measured include axial length type and / or central corneal thickness.

[0043] It can be seen that this optional embodiment can accurately determine the characteristic position information required for measuring human eye-related parameters and the parameter type that can be measured by the characteristic position information from all sub-position information contained in all human eye-related position information; and group all the characteristic position information according to the parameter type corresponding to all the characteristic position information to obtain multiple characteristic position information groups, which is conducive to improving the accuracy and reliability of the grouped characteristic position information groups, and then process all the characteristic position information in each characteristic position information group to obtain the human eye parameters of the parameter type corresponding to the characteristic position information group, which can realize accurate measurement of the human eye parameters of the corresponding parameter type based on the accurately grouped characteristic position information groups, and then determine the human eye parameters of the parameter type corresponding to all the characteristic position information groups as the first type of human eye parameters, which can improve the measurement accuracy and reliability of the first type of human eye parameters based on the segmentation algorithm.

[0044] In this optional embodiment, as an optional implementation manner, each characteristic position information group may specifically include: The position of the highest point on the corneal surface included in the corneal position information and the position of the retinal surface included in the retinal position information; or, The position information of the upper surface of the cornea included in the corneal position information and the position information of the lower surface of the cornea included in the corneal position information; or, The position information of the retinal nerve fiber layer included in the retinal position information and the position information of the extrinsic layer included in the retinal position information; or, The position information of the corneal vertex included in the corneal position information and the position information of the front surface of the lens included in the iris and lens position information; or, The vertex position information of the front surface of the lens included in the iris and lens position information and the vertex position information of the back surface of the lens included in the iris and lens position information; or, The retinal position information includes the position information of the retinal pigment epithelium and the position information of the choroidal junction.

[0045] In the embodiment of the present invention, specifically, processing all feature position information in each feature position information group to obtain the human eye parameter of the parameter type corresponding to the feature position information group may include: For each characteristic position information, when the characteristic position information group includes the highest point position of the corneal surface included in the corneal position information and the retinal surface position included in the retinal position information, a vertical line perpendicular to the corneal surface is drawn at the highest point position, and the vertical line is extended to the retinal surface position, and the length of the vertical line is calculated as the axial length of the human eye; and / or, When the characteristic position information group includes the position information of the upper surface of the cornea and the position information of the lower surface of the cornea contained in the corneal position information, the position difference between the upper surface of the cornea and the lower surface of the cornea is calculated according to the position information of the upper surface of the cornea and the position information of the lower surface of the cornea as the central corneal thickness of the human eye; and / or, When the characteristic position information group includes the position information of the retinal nerve fiber layer and the position information of the outer plexus layer contained in the retinal position information, the position difference between the retinal nerve fiber layer and the outer plexus layer is calculated according to the position information of the retinal nerve fiber layer and the position information of the outer plexus layer as the retinal thickness of the human eye; and / or, When the characteristic position information group includes the position information of the corneal vertex contained in the corneal position information and the position information of the front surface of the lens contained in the iris and lens position information, the position difference between the corneal vertex and the front surface of the lens is calculated according to the position information of the corneal vertex and the position information of the front surface of the lens as the anterior chamber depth of the human eye; and / or, When the characteristic position information group includes the position information of the front surface of the lens and the position information of the back surface of the lens, the position difference between the front surface of the lens and the back surface of the lens is calculated according to the position information of the front surface of the lens and the position information of the back surface of the lens as the lens thickness of the human eye; and / or, When the characteristic position information group includes the position information of the posterior lens capsule and the position information of the retinal nerve fiber epithelium, the retinal nerve fiber epithelium is used as the retinal inner limiting membrane, and the distance between the posterior lens capsule and the retinal inner limiting membrane is calculated according to the position information of the posterior lens capsule and the position information of the retinal nerve fiber epithelium to obtain the vitreous cavity length of the human eye; and / or, When the characteristic position information group includes the position information of the retinal pigment epithelium and the position information of the choroid / sclera junction, the position difference between the retinal pigment epithelium and the choroid / sclera junction is calculated based on the position information of the retinal pigment epithelium and the position information of the choroid / sclera junction as the choroid thickness of the human eye.

[0046] It can be seen that this optional implementation can improve the measurement accuracy and reliability of human eye parameters of the parameter type corresponding to each characteristic position information group by providing characteristic position information groups with diversified information.

[0047] Embodiment 2 See also Figure 5 , Figure 5 FIG. 1 is a flow chart of another method for measuring human eye parameters based on OCT corneal tomographic images disclosed in an embodiment of the present invention. Figure 5 The described method for measuring human eye parameters based on corneal tomographic images of OCT can be applied to a human eye parameter measuring device based on corneal tomographic images of OCT, wherein the device may include a measuring device or a measuring server, wherein the measuring server may include a cloud server or a local server, which is not limited in the embodiments of the present invention. Figure 5 As shown, the method for measuring human eye parameters based on OCT corneal tomographic images may include the following operations: 201. Scan the human eye based on the OCT device to obtain OCT image information of the human eye.

[0048] In an embodiment of the present invention, a specific method for scanning a human eye based on an OCT device to obtain OCT image information of the human eye can be based on a micon scanning mode under a cornea detection mode of the OCT device to scan and obtain multiple OCT images of the human eye at circular intervals, such as: 8, 16 or 32 images.

[0049] 202. Based on a preset segmentation algorithm and according to the OCT image information, determine position information of each segmentation line of the OCT image information.

[0050] 203. Determine multiple pieces of human eye-related position information based on the position information of all segmentation lines.

[0051] 204. Analyze the first type of human eye parameters according to all the human eye related position information.

[0052] 205. Project and synthesize the OCT image to obtain a circular ring image corresponding to the OCT image; and pre-process the circular ring image to obtain a target circular ring image.

[0053] In the embodiment of the present invention, the preprocessing includes smoothing or edge modification. Specifically, integral projection is performed on the OCT images in each direction of the circular interval obtained by scanning to obtain a separated rectangular projection map, and then the rectangular projection map is used to synthesize a circular ring image, and then the circular ring image is smoothed or edge modified to obtain a target circular ring image.

[0054] 206. According to the target circular ring image, find the longest distance of the eyeball boundary of the human eye in the target circular ring image in the horizontal direction in the target circular ring image to obtain a white-to-white parameter.

[0055] In the embodiment of the present invention, the boundary between the eyeball and the pupil can be seen on the donut diagram, and the longest distance of the eyeball boundary, that is, the white-to-white distance, is found in the horizontal direction.

[0056] 207. Perform deformation correction on the OCT image to obtain a corrected OCT image; and measure pupil diameter parameters of the human eye according to the corrected OCT image.

[0057] In the embodiment of the present invention, specifically, the pupil diameter-related image contained in the OCT image is deformed and corrected, so that the pupil diameter parameter of the human eye is measured through the corrected pupil diameter-related image. Figure 6-7 As shown, Figure 6 is a schematic diagram of a pupil diameter-related image before correction disclosed in an embodiment of the present invention, Figure 7 It is a schematic diagram of a corrected pupil diameter-related image disclosed in an embodiment of the present invention.

[0058] In the embodiment of the present invention, there is no order of precedence between step 205-step 207 and step 202-step 204, that is, step 205-step 207 can occur before step 202-step 204, or after step 202-step 204, or can occur simultaneously with step 202-step 204, which is not limited in the embodiment of the present invention.

[0059] 208. Determine a first type of human eye parameter and a second type of human eye parameter as a parameter measurement result of the human eye using the OCT device.

[0060] In the embodiment of the present invention, for other descriptions of steps 201 to 204 and step 208, please refer to the detailed description of steps 101 to 104 and step 106 in the first embodiment, which will not be repeated in the embodiment of the present invention.

[0061] It can be seen that implementation Figure 5The described method for measuring human eye parameters based on OCT corneal tomographic images can scan the human eye based on the OCT device to obtain OCT image information of the human eye; and based on a preset segmentation algorithm, accurately determine the position information of each of the multiple segmentation lines of the OCT image information according to the OCT image information, determine multiple human eye-related position information according to the position information of all the segmentation lines, and can improve the accuracy and efficiency of determining the human eye-related position information in the OCT image based on the segmentation algorithm, analyze the first type of human eye parameters based on all the human eye-related position information, and can improve the first type of human eye parameters based on the human eye-related position information. Measurement accuracy and efficiency; and based on a preset image processing algorithm, processing the OCT image to measure the second type of human eye parameters of the human eye, which can improve the measurement accuracy and efficiency of the second type of human eye parameters based on the image processing algorithm; and then determining the first type of human eye parameters and the second type of human eye parameters as the parameter measurement results of the human eye through the OCT device, by providing a variety of human eye parameter measurement methods can improve the accuracy and richness of the measured human eye biological parameters, can improve the utilization rate of the OCT device by measuring as many human eye biological parameters as possible, but also conducive to improving the subsequent analysis efficiency and analysis accuracy of the human eye biological parameters. In addition, by projecting and synthesizing the scanned OCT image to obtain a donut-shaped diagram and performing various image processing operations such as smoothing or edge modification on it, it is possible to accurately find the longest distance of the eyeball boundary in the processed target donut-shaped diagram to obtain the white-to-white parameter, which is beneficial to improving the accuracy and reliability of the measured white-to-white parameter; and by performing image processing operations for deformation correction on the scanned OCT image, it is possible to accurately measure the pupil diameter parameter of the human eye, and use the white-to-white parameter and the pupil diameter parameter as the second type of human eye parameter, which is beneficial to improving the measurement accuracy and reliability of the second type of human eye parameter based on the image processing algorithm.

[0062] In an optional embodiment, the projecting and synthesizing of the OCT image in step 205 to obtain a circular ring image corresponding to the OCT image may include: Based on the Canny edge detection algorithm, rectangle detection is performed on the OCT image to obtain the rectangular feature data of the OCT image; Based on Hough transform or contour detection algorithm, detect and extract boundary information of rectangular feature data, where the boundary information includes rectangle position information and / or rectangle size information; Calculate the annular region parameters corresponding to the rectangular feature data according to the rectangular position information and the rectangular size information, wherein the annular region parameters include one or more combinations of the inner diameter of the annular region, the outer diameter of the annular region and the center position of the annular region; Based on perspective transformation or affine transformation, according to the annular area parameters, the shape of the rectangle corresponding to the rectangular feature data is transformed to make the rectangle into a circular ring, and the circular ring is updated to the OCT image to replace the rectangle, so as to obtain the circular ring image corresponding to the OCT image.

[0063] In the embodiment of the present invention, specifically, a method based on the Canny edge detection algorithm is first used to perform rectangle detection, and then a Hough transform or contour detection method is used to detect and extract the boundary of the rectangle, and then the parameters of the corresponding annular area, such as the inner diameter, outer diameter and center position, are calculated according to the position and size information of the rectangle. A geometric calculation method can be used, such as calculating the inner diameter and outer diameter by the size of the rectangle, or calculating the center position by the position of the rectangle, and then using a perspective transformation or an affine transformation to transform the shape of the rectangle into a circular ring (such as: applying a transformation matrix to perform a perspective transformation or an affine transformation on the rectangle to change its shape into a circular ring). Specifically, the calculation of the parameters of the annular area can be achieved by calibrating the four corner points of the rectangle and the four corresponding corner points of the target annular area. Specifically, when calibrating a rectangular image, an advanced method such as a deep learning algorithm is used. First, a large number of test and training human eye-related data sets need to be carefully prepared, and then a convolutional neural network (including a VGG network, a ResNet network, and a MobileNet series, etc.) is selected from them to carry out comprehensive processing of this image data set. Then, according to the output results, the parameters of the model are carefully adjusted to continuously improve the performance of the model. After obtaining the final training parameters, the range of white to white and the pupil can be obtained by using the OCT device to capture the human eye image. Then, with the help of the position information of the image, the detailed information of white to white and the pupil diameter can be successfully obtained.

[0064] It can be seen that this optional embodiment can perform rectangle detection on the OCT image based on the Canny edge detection algorithm to obtain rectangular feature data of the OCT image, and detect and extract boundary information of the rectangular feature data based on the Hough transform or contour detection algorithm, the boundary information includes rectangle position information and / or rectangle size information, which can improve the detection accuracy of the rectangle position information and rectangle size information used to determine the annular area of ​​the OCT image; then, based on the rectangle position information and the rectangle size information, the annular area parameters corresponding to the rectangle feature data are accurately calculated; then, based on the perspective transformation or affine transformation method, according to the annular area parameters, the shape of the rectangle corresponding to the rectangle feature data is transformed to change the rectangle into a circular ring, and the circular ring is updated to the OCT image to replace the rectangle, so as to obtain a circular ring image corresponding to the OCT image, which can improve the transformation accuracy and reliability of the OCT image into a circular ring image based on the perspective transformation and the affine transformation.

[0065] In another optional embodiment, the segmentation algorithm includes the shortest path Dijkstra algorithm. And, the above step 202, based on the preset segmentation algorithm, determines the position information of each segmentation line in the multiple segmentation lines of the OCT image information according to the OCT image information, which may include: The brightness value or grayscale value contained in the OCT image information is used as a pixel value to calculate a weight map; the weight map is flattened to obtain a flattened image, and the flattened image includes multiple target layers; Based on the shortest path Dijkstra algorithm, the starting point or center point of each target layer is determined as the source node, and the remaining nodes except the source node are selected from the source node and the contour of the target layer, the path length between the source node and each remaining node is calculated, and the target node with the shortest path length is selected from all the remaining nodes; the line segment between the source node and the target node is determined as the segmentation line of the target layer; the position information of the segmentation line of the target layer is determined according to the position of the source node and the position of the target node in the flattened image; Wherein, all segmentation lines of the OCT image information include segmentation lines of all target layers.

[0066] In an embodiment of the present invention, specifically, when calculating a weight map, taking brightness values ​​as an example, a brighter area may have a higher weight value, while a darker area may have a lower weight value to calculate the weight map. Flattening the weight map to obtain a flattened image may include: flattening the weight map, that is, sorting the pixels in the image according to the weight values ​​to form a one-dimensional image representation, and rearranging the original OCT image according to the sorted pixel values ​​to form a flattened image.

[0067] Optionally, each target layer may include one of a cornea layer, a retina layer, an iris layer, a lens layer, and a choroid layer.

[0068] Taking the retinal layer as an example, the starting point or center point of the retinal layer is selected as the source node. Starting from the source node, multiple other nodes are selected according to the outline of the retinal layer and gradually expanded to other nodes. The shortest path is selected by comparing the path lengths, thereby obtaining the segmentation line for the retinal layer in the OCT image.

[0069] It can be seen that this optional embodiment can use the brightness value or grayscale value contained in the OCT image information as the pixel value to accurately calculate the weight map; and flatten the weight map to obtain a flattened image, which is beneficial to improve the determination accuracy of the flattened image used as the calculation basis of the shortest path length algorithm; then based on the shortest path Dijkstra algorithm, the starting point or center point of each target layer is determined as the source node, and according to the source node and the remaining nodes other than the source node in the contour of the target layer, the path length between the source node and each remaining node is accurately calculated, and the target node with the path length as the shortest path length is selected from all the remaining nodes; the line segment between the source node and the target node is determined as the dividing line of the target layer, which can improve the determination accuracy of the node corresponding to the shortest path length, thereby improving the determination accuracy of the dividing line of each target layer; then according to the position of the source node and the position of the target node in the flattened image, the position information of the dividing line of the target layer is determined, which can improve the determination accuracy and reliability of the dividing line position information.

[0070] In yet another optional embodiment, the method may further include: Obtain the first segmentation line with the lowest steepness value and the second segmentation line with the highest steepness value from all segmentation lines; According to the first dividing line and the second dividing line, fitting the points of the first dividing line and the points of the second dividing line into a circular image to calculate the radius parameter of the circular image; Based on a preset curvature radius calculation formula, the corneal curvature radius of the human eye is calculated according to the radius parameter, and the corneal curvature radius is added to the parameter measurement result of the human eye.

[0071] In the embodiment of the present invention, for the segmentation lines in different directions, the segmentation line with the lowest steepness value and the segmentation line with the highest steepness value are obtained. Then, the least squares fitting method is used to fit each point on the two segmentation lines into a circle. The specific fitting method is: let the equation of the circle be ; where (a, b) is the coordinate of the center of the circle, and r is the radius. For a given series of points (x i ,y i ), the sum of the squares of the distances from these points to the fitting circle should be minimized. The error function can be expressed as: , and then calculate the partial derivatives of a, b, and r respectively, and set them equal to 0 to solve the optimal parameters. In this way, by solving the above equations simultaneously, the curvature radius r of the fitting circle can be obtained. The calculation formula of the corneal curvature radius can be K=(n1-n2) / r, where n1 represents the refractive index of air and n2 represents the refractive index of corneal aqueous humor. In this way, the corneal curvature radius at different angles can be obtained, such as: flat K value and steep K value.

[0072] It can be seen that this optional embodiment can obtain the first dividing line with the lowest steepness value and the second dividing line with the highest steepness value from all dividing lines, and according to the first dividing line and the second dividing line, fit the points of the first dividing line and the points of the second dividing line into a circular image to calculate the radius parameters of the circular image, which can improve the calculation accuracy and reliability of the radius of the circular image; then based on the preset curvature radius calculation formula, according to the radius parameters, the corneal curvature radius of the human eye is accurately calculated, and the corneal curvature radius is added to the parameter measurement results of the human eye, which can improve the diversity and richness of the measured biological parameters of the human eye to a certain extent.

[0073] Embodiment 3 See also Figure 8 , Figure 8 : is a schematic diagram of the structure of a human eye parameter measurement device based on OCT corneal tomographic images disclosed in an embodiment of the present invention. Figure 8 The human eye parameter measurement device based on OCT corneal tomographic images may include a measurement device or a measurement server, wherein the measurement server may include a cloud server or a local server, which is not limited in the embodiment of the present invention. Figure 8 As shown, the human eye parameter measurement device based on the OCT corneal tomographic image may include: The scanning module 301 is used to scan the human eye based on the OCT device to obtain OCT image information of the human eye. The OCT image information includes the brightness value and / or grayscale value of the OCT image.

[0074] The determination module 302 is used to determine the position information of each of the multiple segmentation lines of the OCT image information based on a preset segmentation algorithm and according to the OCT image information, where the segmentation lines are used to segment the OCT image into multiple tomographic images, and the tomographic images at least include corneal tomographic images.

[0075] The determination module 302 is further used to determine multiple human eye related position information based on the position information of all segmentation lines, each human eye related position information includes one of corneal position information, retinal position information, iris and lens position information and choroid position information.

[0076] The analysis module 303 is used to analyze the first type of human eye parameters according to all the human eye related position information.

[0077] The processing module 304 is used to process the OCT image based on a preset image processing algorithm to measure the second type of human eye parameters, where the second type of human eye parameters include white-to-white parameters and pupil diameter parameters.

[0078] The determination module 302 is further used to determine the first type of human eye parameters and the second type of human eye parameters as parameter measurement results of the human eye through the OCT device.

[0079] It can be seen that implementation Figure 8 The described human eye parameter measurement device based on OCT corneal tomographic image can scan the human eye based on the OCT device to obtain OCT image information of the human eye; and based on a preset segmentation algorithm, according to the OCT image information, accurately determine the position information of each of the multiple segmentation lines of the OCT image information, and determine multiple human eye-related position information based on the position information of all the segmentation lines, and can improve the accuracy and efficiency of determining the human eye-related position information in the OCT image based on the segmentation algorithm, analyze the first type of human eye parameters of the human eye based on all the human eye-related position information, and can improve the first type of human eye parameters based on the human eye-related position information. Measurement accuracy and efficiency; and based on a preset image processing algorithm, processing the OCT image to measure the second type of human eye parameters of the human eye, which can improve the measurement accuracy and efficiency of the second type of human eye parameters based on the image processing algorithm; and then determining the first type of human eye parameters and the second type of human eye parameters as the parameter measurement results of the human eye through the OCT device, by providing a variety of human eye parameter measurement methods can improve the accuracy and richness of the measured human eye biological parameters, can improve the utilization rate of the OCT device by measuring as many human eye biological parameters as possible, but also conducive to improving the subsequent analysis efficiency and analysis accuracy of the human eye biological parameters.

[0080] In an optional embodiment, the first type of human eye parameters includes one or more combinations of axial length, central corneal thickness, retinal thickness, anterior chamber depth, lens thickness, vitreous cavity length, and choroid thickness. And, the analysis module 303 analyzes the first type of human eye parameters of the human eye according to all the human eye-related position information, specifically including: According to all the sub-position information included in all the eye-related position information, determining from all the sub-position information the characteristic position information required for measuring the human eye-related parameters and the parameter type that can be measured by the characteristic position information; According to the parameter types corresponding to all the characteristic position information, all the characteristic position information are grouped to obtain a plurality of characteristic position information groups, each characteristic position information group corresponds to a parameter type, and each characteristic position information group includes at least one characteristic position information; Processing all feature position information in each feature position information group to obtain human eye parameters of parameter types corresponding to the feature position information group; The human eye parameters of the parameter types corresponding to all the feature position information groups are determined as the first type of human eye parameters.

[0081] It can be seen that this optional embodiment can accurately determine the characteristic position information required for measuring human eye-related parameters and the parameter type that can be measured by the characteristic position information from all sub-position information contained in all human eye-related position information; and group all the characteristic position information according to the parameter type corresponding to all the characteristic position information to obtain multiple characteristic position information groups, which is conducive to improving the accuracy and reliability of the grouped characteristic position information groups, and then process all the characteristic position information in each characteristic position information group to obtain the human eye parameters of the parameter type corresponding to the characteristic position information group, which can realize accurate measurement of the human eye parameters of the corresponding parameter type based on the accurately grouped characteristic position information groups, and then determine the human eye parameters of the parameter type corresponding to all the characteristic position information groups as the first type of human eye parameters, which can improve the measurement accuracy and reliability of the first type of human eye parameters based on the segmentation algorithm.

[0082] In this optional embodiment, as an optional implementation manner, each characteristic position information group may specifically include: The position of the highest point on the corneal surface included in the corneal position information and the position of the retinal surface included in the retinal position information; or, The position information of the upper surface of the cornea included in the corneal position information and the position information of the lower surface of the cornea included in the corneal position information; or, The position information of the retinal nerve fiber layer included in the retinal position information and the position information of the extrinsic layer included in the retinal position information; or, The position information of the corneal vertex included in the corneal position information and the position information of the front surface of the lens included in the iris and lens position information; or, The vertex position information of the front surface of the lens included in the iris and lens position information and the vertex position information of the back surface of the lens included in the iris and lens position information; or, The retinal position information includes the position information of the retinal pigment epithelium and the position information of the choroidal junction.

[0083] It can be seen that this optional implementation can improve the measurement accuracy and reliability of human eye parameters of the parameter type corresponding to each characteristic position information group by providing characteristic position information groups with diversified information.

[0084] In another optional embodiment, the processing module 304 processes the OCT image based on a preset image processing algorithm to measure the second type of human eye parameters of the human eye, specifically including: Projecting and synthesizing the OCT image to obtain a circular ring image corresponding to the OCT image, and preprocessing the circular ring image to obtain a target circular ring image, wherein the preprocessing includes smoothing or edge modification; and searching the target circular ring image for the longest distance of the eyeball boundary of the human eye in the target circular ring image in the horizontal direction to obtain a white-to-white parameter according to the target circular ring image; The OCT image is deformed and corrected to obtain a corrected OCT image; and the pupil diameter parameter of the human eye is measured according to the corrected OCT image.

[0085] It can be seen that this optional embodiment can project and synthesize the scanned OCT image to obtain a donut-shaped diagram and perform various image processing operations such as smoothing or edge modification on it, so as to accurately find the longest distance of the eyeball boundary in the processed target donut-shaped diagram to obtain the white-to-white parameter, which is beneficial to improving the accuracy and reliability of the measured white-to-white parameter; and by performing image processing operations for deformation correction on the scanned OCT image, it is possible to accurately measure the pupil diameter parameter of the human eye, and use the white-to-white parameter and the pupil diameter parameter as the second type of human eye parameters, which is beneficial to improving the measurement accuracy and reliability of the second type of human eye parameters based on the image processing algorithm.

[0086] In this optional embodiment, as an optional implementation, the processing module 304 projects and synthesizes the OCT image to obtain a circular ring image corresponding to the OCT image, which may specifically include: Based on the Canny edge detection algorithm, rectangle detection is performed on the OCT image to obtain the rectangular feature data of the OCT image; Based on Hough transform or contour detection algorithm, detect and extract boundary information of rectangular feature data, where the boundary information includes rectangle position information and / or rectangle size information; Calculate the annular region parameters corresponding to the rectangular feature data according to the rectangular position information and the rectangular size information, wherein the annular region parameters include one or more combinations of the inner diameter of the annular region, the outer diameter of the annular region and the center position of the annular region; Based on perspective transformation or affine transformation, according to the annular area parameters, the shape of the rectangle corresponding to the rectangular feature data is transformed to make the rectangle into a circular ring, and the circular ring is updated to the OCT image to replace the rectangle, so as to obtain the circular ring image corresponding to the OCT image.

[0087] It can be seen that this optional implementation can perform rectangle detection on the OCT image based on the Canny edge detection algorithm to obtain rectangular feature data of the OCT image, and detect and extract boundary information of the rectangular feature data based on the Hough transform or contour detection algorithm, the boundary information includes rectangle position information and / or rectangle size information, which can improve the detection accuracy of the rectangle position information and rectangle size information used to determine the annular area of ​​the OCT image; then, based on the rectangle position information and the rectangle size information, the annular area parameters corresponding to the rectangle feature data are accurately calculated; then, based on the perspective transformation or affine transformation method, according to the annular area parameters, the shape of the rectangle corresponding to the rectangle feature data is transformed to change the rectangle into a circular ring, and the circular ring is updated to the OCT image to replace the rectangle, so as to obtain a circular ring image corresponding to the OCT image, which can improve the transformation accuracy and reliability of the OCT image into a circular ring image based on the perspective transformation and the affine transformation.

[0088] In another optional embodiment, the segmentation algorithm includes the shortest path Dijkstra algorithm. And, the determination module 302 determines the position information of each segmentation line in the plurality of segmentation lines of the OCT image information based on the preset segmentation algorithm and the OCT image information, and specifically includes: The brightness value or grayscale value contained in the OCT image information is used as a pixel value to calculate a weight map; the weight map is flattened to obtain a flattened image, and the flattened image includes multiple target layers; Based on the shortest path Dijkstra algorithm, the starting point or center point of each target layer is determined as the source node, and the remaining nodes except the source node are selected from the source node and the contour of the target layer, the path length between the source node and each remaining node is calculated, and the target node with the shortest path length is selected from all the remaining nodes; the line segment between the source node and the target node is determined as the segmentation line of the target layer; the position information of the segmentation line of the target layer is determined according to the position of the source node and the position of the target node in the flattened image; Wherein, all segmentation lines of the OCT image information include segmentation lines of all target layers.

[0089] It can be seen that this optional embodiment can use the brightness value or grayscale value contained in the OCT image information as the pixel value to accurately calculate the weight map; and flatten the weight map to obtain a flattened image, which is beneficial to improve the determination accuracy of the flattened image used as the calculation basis of the shortest path length algorithm; then based on the shortest path Dijkstra algorithm, the starting point or center point of each target layer is determined as the source node, and according to the source node and the remaining nodes other than the source node in the contour of the target layer, the path length between the source node and each remaining node is accurately calculated, and the target node with the path length as the shortest path length is selected from all the remaining nodes; the line segment between the source node and the target node is determined as the dividing line of the target layer, which can improve the determination accuracy of the node corresponding to the shortest path length, thereby improving the determination accuracy of the dividing line of each target layer; then according to the position of the source node and the position of the target node in the flattened image, the position information of the dividing line of the target layer is determined, which can improve the determination accuracy and reliability of the dividing line position information.

[0090] In yet another optional embodiment, Fig. 9 As shown, Fig. 9 : is a schematic structural diagram of another device for measuring human eye parameters based on OCT corneal tomographic images disclosed in an embodiment of the present invention, wherein the device may also include: An acquisition module 305 is used to acquire a first segmentation line with the lowest steepness value and a second segmentation line with the highest steepness value from all segmentation lines; A fitting module 306 is used to fit the points of the first dividing line and the second dividing line into a circular image according to the first dividing line and the second dividing line, so as to calculate the radius parameter of the circular image; The calculation module 307 is used to calculate the corneal curvature radius of the human eye based on a preset curvature radius calculation formula and according to the radius parameter, and add the corneal curvature radius to the parameter measurement result of the human eye.

[0091] It can be seen that this optional embodiment can obtain the first dividing line with the lowest steepness value and the second dividing line with the highest steepness value from all dividing lines, and according to the first dividing line and the second dividing line, fit the points of the first dividing line and the points of the second dividing line into a circular image to calculate the radius parameters of the circular image, which can improve the calculation accuracy and reliability of the radius of the circular image; then based on the preset curvature radius calculation formula, according to the radius parameters, the corneal curvature radius of the human eye is accurately calculated, and the corneal curvature radius is added to the parameter measurement results of the human eye, which can improve the diversity and richness of the measured biological parameters of the human eye to a certain extent.

[0092] Embodiment 4 See also Fig.10 , Fig.10FIG. 1 is a schematic diagram of the structure of another device for measuring human eye parameters based on OCT corneal tomographic images disclosed in an embodiment of the present invention. Fig.10 As shown, the human eye parameter measurement device based on the OCT corneal tomographic image may include: A memory 401 storing executable program codes; a processor 402 coupled to the memory 401; The processor 402 calls the executable program code stored in the memory 401 to execute the steps of the method for measuring human eye parameters based on the corneal tomographic image based on OCT described in the first embodiment of the present invention or the second embodiment of the present invention.

[0093] Embodiment 5 An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps of the human eye parameter measurement method based on OCT corneal tomographic images described in Embodiment 1 or Embodiment 2 of the present invention.

[0094] Embodiment 6 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the method for measuring human eye parameters based on OCT corneal tomographic images described in Example 1 or Example 2.

[0095] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0096] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0097] Finally, it should be noted that the human eye parameter measurement method and device based on OCT corneal tomographic images disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for measuring human eye parameters based on corneal tomographic images using OCT, characterized in that: The method comprises: Scanning a human eye based on an OCT device to obtain OCT image information of the human eye, wherein the OCT image information includes a brightness value and / or a grayscale value of the OCT image; Based on a preset segmentation algorithm, according to the OCT image information, determine the position information of each of the plurality of segmentation lines of the OCT image information, wherein the segmentation lines are used to segment the OCT image into a plurality of tomographic images, wherein the tomographic images at least include a corneal tomographic image; Determine a plurality of human eye-related position information according to the position information of all the segmentation lines, each of the human eye-related position information includes one of corneal position information, retinal position information, iris and lens position information, and choroid position information; Analyzing first-category human eye parameters of the human eye according to all the human eye-related position information; Based on a preset image processing algorithm, the OCT image is processed to measure a second type of human eye parameter of the human eye, wherein the second type of human eye parameter includes a white-to-white parameter and a pupil diameter parameter; The first type of human eye parameters and the second type of human eye parameters are determined as parameter measurement results of the human eye by the OCT device.

2. The method for measuring human eye parameters based on corneal tomographic images using OCT according to claim 1, characterized in that: The first type of human eye parameters includes one or more combinations of axial length, central corneal thickness, retinal thickness, anterior chamber depth, lens thickness, vitreous cavity length and choroidal thickness; And, analyzing the first type of human eye parameters of the human eye according to all the human eye related position information includes: According to all the sub-position information included in all the human eye-related position information, determining from all the sub-position information the characteristic position information required for measuring the human eye-related parameters and the parameter type that can be measured by the characteristic position information; According to the parameter types corresponding to all the characteristic position information, all the characteristic position information are grouped to obtain a plurality of characteristic position information groups, each of the characteristic position information groups corresponds to a parameter type, and each of the characteristic position information groups includes at least one characteristic position information; Processing all the feature position information in each of the feature position information groups to obtain human eye parameters of a parameter type corresponding to the feature position information group; Determine human eye parameters of parameter types corresponding to all the feature position information groups as first-category human eye parameters.

3. The method for measuring human eye parameters based on corneal tomographic images using OCT according to claim 2, characterized in that: Each of the characteristic position information groups specifically includes: The corneal position information includes the highest point position of the corneal surface and the retinal surface position included in the retinal position information; or, The position information of the upper surface of the cornea included in the corneal position information and the position information of the lower surface of the cornea included in the corneal position information; or, The position information of the retinal nerve fiber layer included in the retinal position information and the position information of the extrinsic layer included in the retinal position information; or The cornea position information includes the position information of the cornea vertex and the iris and lens position information includes the position information of the front surface of the lens; or, The vertex position information of the front surface of the lens included in the iris and lens position information and the vertex position information of the back surface of the lens included in the iris and lens position information; or, The retinal position information includes the position information of the retinal pigment epithelium and the position information of the choroidal junction.

4. The method for measuring human eye parameters based on OCT corneal tomographic images according to any one of claims 1 to 3, characterized in that: The processing of the OCT image based on a preset image processing algorithm to measure the second type of human eye parameters of the human eye includes: Projecting and synthesizing the OCT image to obtain a circular ring image corresponding to the OCT image, and preprocessing the circular ring image to obtain a target circular ring image, wherein the preprocessing includes smoothing or edge modification; and searching the target circular ring image for the longest distance of the eyeball boundary of the human eye in the target circular ring image in the horizontal direction according to the target circular ring image to obtain the white-to-white parameter; The OCT image is deformed and corrected to obtain a corrected OCT image; and the pupil diameter parameter of the human eye is measured according to the corrected OCT image.

5. The method for measuring human eye parameters based on corneal tomographic images using OCT according to claim 4, characterized in that: The projecting and synthesizing the OCT image to obtain a circular ring image corresponding to the OCT image includes: Based on the Canny edge detection algorithm, rectangle detection is performed on the OCT image to obtain rectangular feature data of the OCT image; Based on Hough transform or contour detection algorithm, detecting and extracting boundary information of the rectangular feature data, wherein the boundary information includes rectangle position information and / or rectangle size information; Calculate the annular region parameters corresponding to the rectangular feature data according to the rectangular position information and the rectangular size information, wherein the annular region parameters include one or more combinations of the inner diameter of the annular region, the outer diameter of the annular region and the center position of the annular region; Based on perspective transformation or affine transformation, according to the annular area parameters, the shape of the rectangle corresponding to the rectangular feature data is transformed to make the rectangle into a circular ring, and the circular ring is updated to the OCT image to replace the rectangle, so as to obtain a circular ring image corresponding to the OCT image.

6. The method for measuring human eye parameters based on corneal tomographic images using OCT according to any one of claims 1, 2, 3 and 5, characterized in that: The segmentation algorithm includes the shortest path Dijkstra algorithm; And, determining the position information of each of the plurality of segmentation lines of the OCT image information based on the preset segmentation algorithm according to the OCT image information includes: The brightness value or grayscale value included in the OCT image information is used as a pixel value to calculate a weight map; the weight map is flattened to obtain a flattened image, wherein the flattened image includes a plurality of target layers; Based on the shortest path Dijkstra algorithm, the starting point or the center point of each target layer is determined as a source node, and the remaining nodes except the source node are selected from the source node and the contour of the target layer, the path length between the source node and each of the remaining nodes is calculated, and the target node whose path length is the shortest path length is selected from all the remaining nodes; the line segment between the source node and the target node is determined as the dividing line of the target layer; the position information of the dividing line of the target layer is determined according to the position of the source node and the position of the target node in the flattened image; Wherein, all segmentation lines of the OCT image information include segmentation lines of all target layers.

7. The method for measuring human eye parameters based on corneal tomographic images using OCT according to claim 6, characterized in that: The method further comprises: Obtaining a first dividing line with the lowest steepness value and a second dividing line with the highest steepness value from all the dividing lines; According to the first dividing line and the second dividing line, fitting the points of the first dividing line and the points of the second dividing line into a circular image to calculate the radius parameter of the circular image; Based on a preset curvature radius calculation formula and according to the radius parameter, the corneal curvature radius of the human eye is calculated, and the corneal curvature radius is added to the parameter measurement result of the human eye.

8. A human eye parameter measurement device based on OCT corneal tomographic images, characterized in that: The device comprises: A scanning module, used to scan a human eye based on an OCT device to obtain OCT image information of the human eye, wherein the OCT image information includes a brightness value and / or a grayscale value of the OCT image; A determination module, configured to determine, based on a preset segmentation algorithm and according to the OCT image information, position information of each of a plurality of segmentation lines of the OCT image information, wherein the segmentation lines are used to segment the OCT image into a plurality of tomographic images, wherein the tomographic images at least include a corneal tomographic image; The determination module is further used to determine a plurality of human eye-related position information according to the position information of all the segmentation lines, each of the human eye-related position information includes one of corneal position information, retinal position information, iris and lens position information, and choroid position information; An analysis module, used for analyzing a first type of human eye parameter of the human eye according to all the human eye related position information; a processing module, configured to process the OCT image based on a preset image processing algorithm to measure a second type of human eye parameter of the human eye, wherein the second type of human eye parameter includes a white-to-white parameter and a pupil diameter parameter; The determination module is further used to determine the first type of human eye parameters and the second type of human eye parameters as parameter measurement results of the human eye through the OCT device.

9. A human eye parameter measurement device based on OCT corneal tomographic images, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for measuring human eye parameters based on OCT corneal tomographic images as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the human eye parameter measurement method based on OCT corneal tomographic images as described in any one of claims 1-7.

Images