Disc region structure hierarchy determination method and device, and electronic device

Abstract

The application provides a disc area structure level determination method and device and electronic equipment. A first area containing a disc area is scanned line by line to obtain OCT volume data. A center point of the first area is taken as a center to star-type sample the OCT volume data to obtain a first number of first BScan two-dimensional section image data. An initial center point of the disc area is determined, and the OCT volume data is star-type sampled with the initial center point as the center to obtain a second number of second BScan two-dimensional section image data. The structure level of the disc area is determined. The OCT volume data is obtained in a line-by-line scanning manner, which ensures a high sampling rate. The sampled data is uniform and continuous. Star-type sampling is performed on the continuous data, which can avoid jumping and errors. In addition, the initial center point of the disc area is determined through star-type sampling, and then star-type sampling is performed with the initial center point as the center, which can obtain a more accurate disc area structure level.

Description

Technical Field

[0001] This invention relates to the field of image data processing technology, and in particular to a method, apparatus, and electronic device for determining the structural hierarchy of the visual disc region. Background Technology

[0002] The optic disc, or "optic nerve disc," is a normal physiological concave shape. Abnormalities such as optic disc bulging indicate potential pathological changes. Medical measurements, such as optic disc size, based on tomographic images of the optic disc and surrounding areas can significantly aid in the early diagnosis and treatment of diseases like glaucoma. Measuring the size and location of the optic disc requires analyzing the hierarchical structure of the eye tissues in the optic disc and surrounding area. Current OCT (Optical Coherence Tomography) techniques for scanning the optic disc primarily employ either progressive or star-shaped scanning methods. Progressive scanning offers the problem that the hierarchical analysis of the optic disc is only continuous within a single image. When using a star-shaped method to present the layered results by angle, the results are a composite of analyses from several progressively scanned images, potentially leading to jumps and errors in the layering results. Star-shaped scanning, on the other hand, suffers from non-uniform sampling across the entire scanning area, with denser sampling in the center and sparser sampling at the boundaries, resulting in a lower sampling rate and poor examination results at the optic disc boundaries. Summary of the Invention

[0003] The purpose of this invention is to provide a method, apparatus, and electronic device for determining the structural hierarchy of the visual disc region, so as to obtain a more accurate structural hierarchy of the visual disc region.

[0004] This invention provides a method for determining the structural hierarchy of the optic disc region. The method includes: scanning a first region of the user's eye containing the optic disc region line by line to obtain OCT volume data; using the center point of the first region as the star-shaped sampling center, performing star-shaped sampling on the OCT volume data to obtain a first number of first BScan two-dimensional cross-sectional image data; determining the initial center point of the optic disc region based on each first BScan two-dimensional cross-sectional image data; using the initial center point as the star-shaped sampling center, performing star-shaped sampling again on the OCT volume data to obtain a second number of second BScan two-dimensional cross-sectional image data; and determining the structural hierarchy of the optic disc region based on each second BScan two-dimensional cross-sectional image data.

[0005] Furthermore, the step of determining the initial center point of the visual disk region based on each first BScan two-dimensional section image data includes: performing semantic segmentation on each first BScan two-dimensional section image data to determine the first visual disk structure layering result of each first BScan two-dimensional section image data; filling the boundaries of each first visual disk structure layering result according to the physical distance between the center point of the first region and the four vertices of the first region; converting each filled first visual disk structure layering result into a first polar coordinate layering result in a polar coordinate system, and converting the first polar coordinate layering result into a first rectangular coordinate layering result in a rectangular coordinate system; determining the position of the first region in the first rectangular coordinate layering result according to the center point of the first region; extracting the first layering result corresponding to the first region from the first rectangular coordinate layering result according to the position of the first region; determining the first Bruch membrane opening region according to the first layering result, and determining the centroid of the first Bruch membrane opening region as the initial center point of the visual disk region.

[0006] Furthermore, the step of filling the boundary of each first visual disk structure layering result based on the physical distance between the center point of the first region and the four vertices of the first region includes: calculating the first physical distance between the center point of the first region and the four vertices of the first region respectively; taking the maximum distance among the multiple first physical distances as the first radius of the first circumscribed circle, and filling the boundary of each first visual disk structure layering result based on the first radius, so that the range covered by each first visual disk structure layering result after filling corresponds to the diameter of the first circumscribed circle.

[0007] Furthermore, the step of determining the structural hierarchy of the optic disc region based on each second BScan two-dimensional section image data includes: performing semantic segmentation on each second BScan two-dimensional section image data to determine the second optic disc structural layering result for each second BScan two-dimensional section image data; filling the boundaries of each second optic disc structural layering result according to the physical distance between the initial center point and the four vertices of the first region; converting each filled second optic disc structural layering result into a second polar coordinate layering result in a polar coordinate system, and converting the second polar coordinate layering result into a second rectangular coordinate layering result in a rectangular coordinate system; determining the position of the second region of the first region in the second rectangular coordinate layering result according to the initial center point; extracting the second layering result corresponding to the first region from the second rectangular coordinate layering result according to the position of the second region; and determining the structural hierarchy of the optic disc region based on the second layering result.

[0008] Furthermore, the step of filling the boundary of each second visual disk structure layering result based on the physical distance between the initial center point and the four vertices of the first region includes: calculating the second physical distance between the initial center point and the four vertices of the first region respectively; taking the maximum distance among the multiple second physical distances as the second radius of the second circumcircle; and filling the boundary of each second visual disk structure layering result based on the second radius, so that the area covered by each second visual disk structure layering result after filling corresponds to the diameter of the second circumcircle.

[0009] Furthermore, the method also includes: determining the second Bruch membrane opening region based on the second layering result; and determining the centroid of the second Bruch membrane opening region as the target center point of the visual disc region.

[0010] Furthermore, the second quantity is greater than the first quantity; each first BScan two-dimensional cross-sectional image data is sampled at a first interval angle; each second BScan two-dimensional cross-sectional image data is sampled at a second interval angle; wherein, the first interval angle is greater than the second interval angle.

[0011] This invention provides a device for determining the structural hierarchy of the optic disc region. The device includes: an acquisition module for scanning a first region of a user's eye containing the optic disc region line by line to acquire OCT volume data; a first sampling module for performing star-shaped sampling on the OCT volume data with the center point of the first region as the star-shaped sampling center to obtain a first number of first BScan two-dimensional cross-sectional image data; a first determination module for determining an initial center point of the optic disc region based on each first BScan two-dimensional cross-sectional image data; a second sampling module for performing star-shaped sampling again on the OCT volume data with the initial center point as the star-shaped sampling center to obtain a second number of second BScan two-dimensional cross-sectional image data; and a second determination module for determining the structural hierarchy of the optic disc region based on each second BScan two-dimensional cross-sectional image data.

[0012] The present invention provides an electronic device, including a processor and a memory, wherein the memory stores machine-executable instructions that can be executed by the processor, and the processor executes the machine-executable instructions to implement the disc region structure hierarchy determination method described above.

[0013] The present invention provides a machine-readable storage medium storing machine-executable instructions. When the machine-executable instructions are invoked and executed by a processor, the machine-executable instructions cause the processor to implement any of the above-mentioned methods for determining the visual disc region structure hierarchy.

[0014] The present invention provides a method, apparatus, and electronic device for determining the structural hierarchy of the optic disc region. The method involves scanning a first region containing the optic disc region line by line to acquire OCT volume data; using the center point of the first region as the center, performing star-shaped sampling of the OCT volume data to obtain a first quantity of first BScan two-dimensional cross-sectional image data; determining the initial center point of the optic disc region; and using this as the center, performing star-shaped sampling of the OCT volume data to obtain a second quantity of second BScan two-dimensional cross-sectional image data, thereby determining the structural hierarchy of the optic disc region. This method acquires OCT volume data through line-by-line scanning, ensuring a high sampling rate and uniform, continuous data. Performing star-shaped sampling on continuous data avoids jumps and errors. Furthermore, first determining the initial center point of the optic disc region through star-shaped sampling, and then performing star-shaped sampling with the initial center point as the center, yields a more accurate structural hierarchy of the optic disc region. Attached Figure Description

[0015] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of a visual disc analysis result provided in an embodiment of the present invention;

[0017] Figure 2 This is a schematic diagram of a line-by-line scanning method provided in an embodiment of the present invention;

[0018] Figure 3 This is a schematic diagram of a star-shaped scanning method provided in an embodiment of the present invention;

[0019] Figure 4 A flowchart of a method for determining the structural hierarchy of a visual disc region provided in an embodiment of the present invention;

[0020] Figure 5 This is a schematic diagram of a line-by-line scanning method provided in an embodiment of the present invention;

[0021] Figure 6 This is a schematic diagram of a star-shaped scanning method provided in an embodiment of the present invention;

[0022] Figure 7 This is a schematic diagram of a star-shaped scanning method provided in an embodiment of the present invention;

[0023] Figure 8 This is a schematic diagram illustrating the relationship between a first region and its circumscribed circle, provided as an embodiment of the present invention.

[0024] Figure 9 A schematic diagram illustrating the physical positional relationship between a first region, a second polar coordinate layering result, and a second rectangular coordinate layering result, provided for an embodiment of the present invention;

[0025] Figure 10 This is a schematic diagram of a device for determining the structural hierarchy of a viewing disk region, provided in an embodiment of the present invention.

[0026] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0027] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] Currently, the optic disc is short for the optic nerve disc, located about 3 mm nasally at the posterior pole of the eyeball. It is typically a 1.5 mm diameter disc with a normal physiological cupping. Abnormalities such as optic disc bulging, enlarged optic disc cupping, optic disc atrophy, and linear hemorrhages around the optic disc indicate potential pathological changes. Medical measurements, such as optic disc size and cup-to-disc ratio, based on tomographic images of the optic disc and surrounding area can further aid in the early diagnosis and treatment of diseases like glaucoma and optic nerve fiber layer defects. Measuring the size and location of the optic disc requires analyzing the hierarchical structure of the eye tissues in the optic disc and surrounding area.

[0029] Because the optic disc is physiologically disc-shaped, optic disc analysis results are mostly presented in a star-shaped pattern, providing examination and analysis results from different angles, such as... Figure 1 The diagram shown is a schematic representation of a video disc analysis result. Figure 1 The left image shows the sampling location of the star-shaped sampling, and the right image shows the corresponding examination and analysis results. However, existing OCT technology for scanning the optic disc region primarily uses either line-by-line scanning or star-shaped scanning methods, such as... Figure 2 A schematic diagram of a progressive scan method is shown. Figure 3The diagram shows a star-shaped scanning method. The advantage of line-by-line scanning and analysis is that it can achieve uniform sampling of the entire scanning area. The disadvantage is that the structural hierarchy analysis results of the visual disk area are based on line-by-line scanning images, so the hierarchy is only continuous on a single image. When the layering results are presented by angle in a star shape, the results are a summation of analysis results from related areas of several line-by-line scanning images. Since each analysis result is independent, the layering results may have jumps or errors.

[0030] The advantage of star-shaped scanning and analysis of the optic disc region is that the image is scanned in a star shape, so the structural hierarchy analysis results change continuously along the star direction. The disadvantage is that the entire scanning area is non-uniformly sampled, with dense sampling in the middle and sparse sampling at the boundaries, resulting in a low sampling rate in the optic disc boundary region and poor examination results. Based on this, embodiments of the present invention provide a method, apparatus, and electronic device for determining the structural hierarchy of the optic disc region. This technology can be applied to applications requiring the detection of the structural hierarchy of the optic disc region.

[0031] To facilitate understanding of this embodiment, a method for determining the hierarchical structure of the visual disc region disclosed in this embodiment will first be introduced, such as... Figure 4 As shown, the method includes the following steps:

[0032] Step S402: Scan the first region of the user's eye, including the optic disc region, line by line to obtain OCT volume data.

[0033] The aforementioned first region can be the same size as the optic disc region. To better ensure the integrity of the data of the detected optic disc region, this first region is usually an area that includes the optic disc region and is slightly larger than it. The shape of this first region can be selected according to actual needs, such as a rectangular region. OCT is an imaging technology that forms fundus images. Because it can reflect the reflection and scattering characteristics of different physiological structures of the fundus to incident weakly coherent light, the formed three-dimensional images have depth information, which has unique advantages compared to fundus color photography and other images. In actual implementation, based on OCT technology, the three-dimensional OCT volume data of the first region of the user's eye, including the optic disc region, can be obtained by scanning line by line. See [link to relevant documentation]. Figure 5 The diagram shows a line-by-line scanning method, which ensures a high sampling rate.

[0034] Step S404: Using the center point of the first region as the star-shaped sampling center, star-shaped sampling is performed on the OCT volume data to obtain the first number of first BScan two-dimensional cross-sectional image data.

[0035] Obtain the center point of the first region. For example, if the first region is a rectangular region, the intersection of the two diagonals of the rectangle can be used as the center point. The first quantity can be set according to actual needs, for example, the first quantity can be 8, 10, etc. Using this center point as the star-shaped sampling center, star-shaped sampling is performed on the OCT volume data to extract the first quantity of first BScan two-dimensional cross-sectional image data. Usually, the extraction is performed using an equally spaced angle method. This first BScan two-dimensional cross-sectional image data can be understood as a two-dimensional cross-sectional view. For example, see [link to relevant documentation]. Figure 6 The diagram illustrates a star-shaped scanning method, which can extract eight first BScan two-dimensional cross-sectional image data at equal intervals. However, if star-shaped sampling is performed directly without first scanning line by line, problems such as non-uniform sampling and a dense middle section with sparse boundaries will still exist.

[0036] Step S406: Determine the initial center point of the visual disc region based on each first BScan two-dimensional cross-sectional image data.

[0037] After obtaining the first number of first BScan two-dimensional cross-sectional image data, a corresponding algorithm can be executed to preliminarily determine the initial center point of the visual disc region; for example, semantic segmentation, coordinate transformation and other processing can be performed on the first number of first BScan two-dimensional cross-sectional image data to preliminarily estimate the initial center point of the visual disc region.

[0038] Step S408: Using the initial center point as the star-shaped sampling center, perform star-shaped sampling on the OCT volume data again to obtain the second number of second BScan two-dimensional cross-sectional image data.

[0039] The second quantity mentioned above can be set according to actual needs, for example, it can be 16, 20, etc.; the second quantity can be the same as or different from the first quantity. For example, if the first quantity is sufficient, the second quantity can be the same as the first quantity. Since the collected data is rich enough, a more accurate visual disc region structure hierarchy can be obtained. In practical applications, considering the computational load, in order to minimize the computational load and improve computational efficiency while ensuring an accurate visual disc region structure hierarchy, the first quantity is usually a smaller quantity, and the second quantity is usually larger than the first quantity. That is, the OCT volume data is sampled in a star pattern with the center point of the first region as the star sampling center. Coarse sampling, using the initial center point as the star-shaped sampling center, involves performing star-shaped sampling again on the OCT volume data for fine sampling. The number of iterations for this fine sampling can be one or more, depending on actual needs. Using the initially estimated initial center point as the star-shaped sampling center, star-shaped sampling is performed again on the OCT volume data to extract a second number of second BScan 2D cross-sectional image data. This is typically done using a denser, equally spaced angle sampling method; that is, each first BScan 2D cross-sectional image data is sampled at a first interval angle, and each second BScan 2D cross-sectional image data is sampled at a second interval angle. The first interval angle is greater than the second interval angle. This second BScan 2D cross-sectional image data can be understood as a 2D cross-sectional view, for example, see [reference needed]. Figure 7 The diagram shows a star-shaped scanning method, which can extract 16 second BScan two-dimensional cross-sectional image data at equal intervals.

[0040] Step S410: Based on the two-dimensional cross-sectional image data of each second BScan, determine the structural hierarchy of the visual disc region.

[0041] After obtaining the second number of second BScan two-dimensional cross-sectional image data, corresponding algorithms can be executed to determine the structural hierarchy of the optic disc region; for example, semantic segmentation and other processing can be performed on the second number of second BScan two-dimensional cross-sectional image data to identify the structural hierarchy of the optic disc region.

[0042] In this method, OCT volume data is sampled by scanning line by line. Star-shaped sampling is then performed on the OCT volume data. A preset layering algorithm is typically applied to the star-shaped sampled image to smooth the layer lines, ensuring they are continuous and without abrupt changes. Since different image stitching processes are not required, abrupt changes are effectively avoided. Taking a second quantity greater than the first quantity as an example, coarse sampling is performed first to obtain a coarsely calculated initial center point of the optic disc region. Then, fine sampling is performed to obtain a more accurate structural hierarchy of the optic disc region, and consequently, a more accurate center point of the optic disc region.

[0043] The aforementioned method for determining the structural hierarchy of the optic disc region involves scanning a first region containing the optic disc line by line to acquire OCT volume data. Using the center point of the first region as the center, star-shaped sampling of the OCT volume data is performed to obtain a first quantity of first BScan two-dimensional cross-sectional image data. An initial center point of the optic disc region is determined, and using this center as the center, star-shaped sampling of the OCT volume data is performed to obtain a second quantity of second BScan two-dimensional cross-sectional image data. Finally, the structural hierarchy of the optic disc region is determined. This method acquires OCT volume data through line-by-line scanning, ensuring a high sampling rate. The sampled data is uniform and continuous. Performing star-shaped sampling on continuous data avoids jumps and errors. Furthermore, first determining the initial center point of the optic disc region through star-shaped sampling, and then performing star-shaped sampling around this initial center point, yields a more accurate structural hierarchy of the optic disc region.

[0044] This invention also provides another method for determining the hierarchical structure of the visual disc region, which is implemented based on the method in the above embodiments. The method includes the following steps:

[0045] Step 1: Scan the first region of the user's eye, including the optic disc area, line by line to obtain OCT volume data.

[0046] Step 2: Using the center point of the first region as the star-shaped sampling center, perform star-shaped sampling on the OCT volume data to obtain the first number of first BScan two-dimensional cross-sectional image data.

[0047] Step 3: Perform semantic segmentation on each first BScan two-dimensional section image data to determine the first spectral structure layering result of each first BScan two-dimensional section image data.

[0048] Semantic segmentation assigns a category to each pixel in an image, achieving pixel-level classification. In practice, semantic segmentation can be performed on each first BScan 2D cross-sectional image data to obtain the first optic disc structure layering result corresponding to each first BScan 2D cross-sectional image data.

[0049] Step 4: Based on the physical distance between the center point of the first region and the four vertices of the first region, perform boundary filling on each first visual disk structure layering result.

[0050] Step four can be achieved through steps A and B:

[0051] Step A: Calculate the first physical distance between the center point of the first region and the four vertices of the first region.

[0052] In actual implementation, the first region is usually a rectangular region with four vertices. The first physical distance between the center point of the rectangular region and the four vertices of the first region can be calculated. It can be understood that the first physical distance between the center point and each vertex is usually the same.

[0053] Step B involves using the maximum distance among multiple first physical distances as the first radius of the first circumcircle, and filling the boundary of each first visual disk structure layering result based on the first radius, so that the area covered by each first visual disk structure layering result after filling corresponds to the diameter of the first circumcircle.

[0054] If each first physical distance is not exactly the same, the maximum distance among multiple first physical distances can be used as the first radius of the first circumcircle; if each first physical distance is the same, any one of the first physical distances can be used as the first radius of the circumcircle. The circumcircle of the first region is drawn with the center point of the first region as the center and the first radius as the radius. The boundary of each first view disk structure layering result is filled according to the first radius. For example, the area to be filled can be repeatedly filled according to the original data at the boundary, so that the area covered by each first view disk structure layering result after filling is the diameter of the circumcircle.

[0055] Step 5: Convert the layered result of each first visual disk structure after filling into the first polar coordinate layered result in the polar coordinate system, and convert the first polar coordinate layered result into the first rectangular coordinate layered result in the rectangular coordinate system.

[0056] Each first-view disk structure layering result after filling is usually based on a single BScan. Each first-view disk structure layering result after filling can be spliced ​​and combined to convert it into a first polar coordinate layering result in polar coordinates. The specific splicing and combination methods can be referred to relevant technologies, which will not be elaborated here. Furthermore, the first polar coordinate layering result in polar coordinates is converted into a first rectangular coordinate layering result in rectangular coordinates. The purpose of coordinate transformation is mainly to facilitate the display of layers and the retrieval of specific layer values.

[0057] Step 6: Determine the position of the first region in the first right-angle coordinate layering result based on the center point of the first region.

[0058] Based on the center point of the first region, the position of the original first region in the first rectangular coordinate layering result can be calculated. Specifically, the data filled in the area to be filled in step B can be removed from the coverage area corresponding to the first rectangular coordinate layering result to obtain the position of the first region in the coverage area corresponding to the first rectangular coordinate layering result.

[0059] Step 7: Based on the location of the first region, extract the first layer result corresponding to the first region from the first rectangular coordinate layer result.

[0060] In actual implementation, the first rectangular coordinate layering result usually contains the layering results corresponding to the original first region and the filled region; therefore, based on the position of the first region, the first layering result corresponding to the original first region can be cut out from the first rectangular coordinate layering result and saved, ensuring that the finally saved first layering result matches the original first region.

[0061] Step 8: Determine the first Bruch membrane opening region based on the first layering result, and determine the centroid of the first Bruch membrane opening region as the initial center point of the visual disk region.

[0062] The Bruch membrane mentioned above refers to the segment between the retinal pigment epithelium and the choroid, and can be used to regulate the metabolism between the two. Based on the first layering result, the opening region of the Bruch membrane can be automatically determined. For example, the location where the layering lines in the first layering result coincide can be determined as the opening region of the Bruch membrane, which is the boundary of the optic disc region. Then, the centroid of this optic disc region is calculated, and this centroid is used as the initial center point of the optic disc region. This initial center point may be the same as or different from the center point of the first region.

[0063] Step 9: Using the initial center point as the star-shaped sampling center, perform star-shaped sampling on the OCT volume data again to obtain the second number of second BScan two-dimensional cross-sectional image data.

[0064] Step 10: Perform semantic segmentation on each second BScan two-dimensional section image data to determine the second spectral structure layering result of each second BScan two-dimensional section image data.

[0065] In practice, semantic segmentation can be performed on each second BScan two-dimensional section image data to obtain the second spectral structure layering result corresponding to each second BScan two-dimensional section image data.

[0066] Step 11: Fill the boundaries of each second visual disk structure layering result based on the physical distance between the initial center point and the four vertices of the first region;

[0067] This step eleven can be achieved through the following steps C and D:

[0068] Step C: Calculate the second physical distance between the initial center point and the four vertices of the first region.

[0069] In actual implementation, the second physical distance between the initial center point of the viewing disk area and the four vertices of the first area can be calculated. Since the initial center point of the viewing disk area and the center point of the first area may be the same or different, the second physical distance between the initial center point and each vertex may be the same or different.

[0070] Step D: Take the maximum distance among multiple second physical distances as the second radius of the second circumcircle, and fill the boundary of each second visual disk structure layering result based on the second radius, so that the range covered by each second visual disk structure layering result after filling corresponds to the diameter of the second circumcircle.

[0071] If all second physical distances are the same, any one of them can be used as the second radius of the circumcircle. If the second physical distances are not exactly the same, the largest distance among them can be used as the second radius of the second circumcircle. Using the initial center point of the viewing disk region as the center and the second radius as the radius, the circumcircle of the first region is drawn again. The boundary of each second viewing disk structure layering result is then filled according to the second radius. For example, see... Figure 8 The diagram shown illustrates the relationship between the first region and the circumscribed circle. The region to be filled can be repeatedly filled based on the original data at the boundary, so that the area covered by each layered result of the second viewing disk structure after filling is the diameter of the circumscribed circle.

[0072] Step 12: Convert the layered result of each second view disk structure after filling into a second polar coordinate layered result in a polar coordinate system, and convert the second polar coordinate layered result into a second rectangular coordinate layered result in a rectangular coordinate system.

[0073] Each layered result of the second view disk structure after filling is based on a single BScan. The layered results of each layered result of the second view disk structure after filling can be combined and preprocessed to convert them into second polar coordinate layered results in polar coordinate system. Furthermore, the second polar coordinate layered results in polar coordinate system are converted into second rectangular coordinate layered results in rectangular coordinate system. The purpose of coordinate transformation is to facilitate the display of layers and the calling of specific values ​​of layers.

[0074] like Figure 9 The diagram shows the physical positional relationship between the first region, the second polar coordinate segmentation result, and the second rectangular coordinate segmentation result. It can be seen that the image region in the middle containing the viewing disk region is the original scanning region (corresponding to the first region mentioned above), the region corresponding to the circumscribed circle is the coverage region corresponding to the second polar coordinate segmentation result in the polar coordinate system, and the region corresponding to the circumscribed rectangle of the circumscribed circle is the coverage region corresponding to the second rectangular coordinate segmentation result in the rectangular coordinate system.

[0075] Step 13: Determine the position of the second region in the second rectangular coordinate layering result of the first region based on the initial center point.

[0076] Based on the initial center point of the viewing area, the position of the second region in the second rectangular coordinate layering result of the original first region can be calculated. Specifically, the data filled in the area to be filled in step D can be removed from the coverage area corresponding to the layering result of the second rectangular coordinate system to obtain the position of the second region in the coverage area corresponding to the layering result of the second rectangular coordinate system.

[0077] Step fourteen: Based on the location of the second region, extract the second layering result corresponding to the first region from the second rectangular coordinate layering result.

[0078] In practice, the second rectangular coordinate layering result usually contains the layering results corresponding to the original first region and the filled region. Therefore, based on the position of the second region, the second layering result corresponding to the original first region can be cut out from the second rectangular coordinate layering result and saved, ensuring that the finally saved second layering result matches the original first region.

[0079] Step 15: Determine the structural hierarchy of the visual disc region based on the second layering results.

[0080] Step sixteen: Determine the opening region of the second Bruch membrane based on the second layering results.

[0081] Step 17: Determine the centroid of the opening region of the second Bruch membrane as the target center point of the visual disc region.

[0082] The Bruch membrane opening region can be automatically determined based on the second layering results. For example, the location where the layering lines in the second layering results coincide can be identified as the Bruch membrane opening region, which is the boundary of the visual disc region. Then, the centroid of this visual disc region is calculated and used as the target center point of the visual disc region. This target center point may be the same as or different from the initial center point of the visual disc region, but it is usually closer to the actual center point of the visual disc region. If the fine sampling is repeated multiple times, except for the star-shaped sampling center used in the first fine sampling, which can be the initial center point of the visual disc region, the star-shaped sampling center used in each subsequent fine sampling can be the target center point of the visual disc region obtained after the analysis of the previous fine sampling.

[0083] The aforementioned method for determining the hierarchical structure of the optic disc region, through coarse and fine sampling, can obtain highly accurate hierarchical analysis results of the optic disc region structure while minimizing computational load. When acquiring OCT volume data of the first region containing the optic disc region, scanning in a line-by-line manner can obtain uniform sampling results. Using the center point of the first region as the star center point, star-shaped coarse sampling and semantic segmentation are performed on the OCT volume data to roughly calculate the initial center point of the optic disc region. Then, using the initial center point as the star center point, star-shaped fine sampling and semantic segmentation are performed on the OCT volume data to obtain a more accurate hierarchical segmentation result of the optic disc region structure, thereby calculating a more accurate position of the optic disc center point.

[0084] This invention provides a device for determining the structural hierarchy of a visual disc region, such as... Figure 10 As shown, the device includes: an acquisition module 100, used to scan a first region of the user's eye containing the optic disc region line by line to acquire OCT volume data; a first sampling module 101, used to perform star-shaped sampling on the OCT volume data with the center point of the first region as the star-shaped sampling center to obtain a first number of first BScan two-dimensional cross-sectional image data; a first determination module 102, used to determine the initial center point of the optic disc region based on each first BScan two-dimensional cross-sectional image data; a second sampling module 103, used to perform star-shaped sampling on the OCT volume data again with the initial center point as the star-shaped sampling center to obtain a second number of second BScan two-dimensional cross-sectional image data; and a second determination module 104, used to determine the structural hierarchy of the optic disc region based on each second BScan two-dimensional cross-sectional image data.

[0085] The aforementioned device for determining the structural hierarchy of the optic disc region acquires OCT volume data by scanning line by line, ensuring a high sampling rate. The sampled data is uniform and continuous. Star-shaped sampling on continuous data can avoid jumps and errors. In addition, the initial center point of the optic disc region is determined by star-shaped sampling first, and then star-shaped sampling is performed with the initial center point as the center, which can obtain a more accurate structural hierarchy of the optic disc region.

[0086] Furthermore, the first determining module 102 is also used to: perform semantic segmentation on each first BScan two-dimensional cross-sectional image data to determine the first visual disk structure layering result of each first BScan two-dimensional cross-sectional image data; fill the boundaries of each first visual disk structure layering result according to the physical distance between the center point of the first region and the four vertices of the first region; convert each filled first visual disk structure layering result into a first polar coordinate layering result in polar coordinates, and convert the first polar coordinate layering result into a first rectangular coordinate layering result in rectangular coordinates; determine the position of the first region in the first rectangular coordinate layering result according to the center point of the first region; extract the first layering result corresponding to the first region from the first rectangular coordinate layering result according to the position of the first region; determine the first Bruch membrane opening region according to the first layering result, and determine the centroid of the first Bruch membrane opening region as the initial center point of the visual disk region.

[0087] Furthermore, the first determining module 102 is also used to: calculate the first physical distance between the center point of the first region and the four vertices of the first region respectively; take the maximum distance among the multiple first physical distances as the first radius of the first circumscribed circle, and fill the boundary of each first visual disk structure layering result based on the first radius, so that the range covered by each first visual disk structure layering result after filling corresponds to the diameter of the first circumscribed circle.

[0088] Furthermore, the second determining module 103 is also used to: perform semantic segmentation on each second BScan two-dimensional cross-sectional image data to determine the second optic disc structure layering result of each second BScan two-dimensional cross-sectional image data; fill the boundaries of each second optic disc structure layering result according to the physical distance between the initial center point and the four vertices of the first region; convert each filled second optic disc structure layering result into a second polar coordinate layering result in a polar coordinate system, and convert the second polar coordinate layering result into a second rectangular coordinate layering result in a rectangular coordinate system; determine the position of the second region of the first region in the second rectangular coordinate layering result according to the initial center point; extract the second layering result corresponding to the first region from the second rectangular coordinate layering result according to the position of the second region; and determine the structural hierarchy of the optic disc region based on the second layering result.

[0089] Furthermore, the second determining module 103 is also used to: calculate the second physical distance between the initial center point and the four vertices of the first region respectively; take the maximum distance among the multiple second physical distances as the second radius of the second circumcircle, and fill the boundary of each second visual disk structure layering result based on the second radius, so that the range covered by each second visual disk structure layering result after filling corresponds to the diameter of the second circumcircle.

[0090] Furthermore, the second determining module 103 is also used to: determine the second Bruch membrane opening region based on the second layering result; and determine the centroid of the second Bruch membrane opening region as the target center point of the viewing disk region.

[0091] Furthermore, the second quantity is greater than the first quantity; each first BScan two-dimensional cross-sectional image data is sampled at a first interval angle; each second BScan two-dimensional cross-sectional image data is sampled at a second interval angle; wherein, the first interval angle is greater than the second interval angle.

[0092] The disc region structure hierarchy determination device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned disc region structure hierarchy determination method embodiment. For the sake of brevity, any parts not mentioned in the disc region structure hierarchy determination device embodiment can be referred to the corresponding content in the aforementioned disc region structure hierarchy determination method embodiment.

[0093] This invention also provides an electronic device, see [link to relevant documentation]. Figure 11 As shown, the electronic device includes a processor 130 and a memory 131. The memory 131 stores machine-executable instructions that can be executed by the processor 130. The processor 130 executes the machine-executable instructions to implement the above-described method for determining the structure hierarchy of the video disc area.

[0094] Furthermore, Figure 11 The electronic device shown also includes a bus 132 and a communication interface 133, with the processor 130, the communication interface 133 and the memory 131 connected via the bus 132.

[0095] The memory 131 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 133 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network. The bus 132 may be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 11 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0096] Processor 130 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 130 or by instructions in software form. Processor 130 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 131, and processor 130 reads the information in memory 131 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0097] This invention also provides a machine-readable storage medium storing machine-executable instructions. When these machine-executable instructions are invoked and executed by a processor, they cause the processor to implement the above-described method for determining the structure hierarchy of the visual disc region. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0098] The computer program product of the method, apparatus and electronic device for determining the structure hierarchy of the visual disc region provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation, please refer to the method embodiments, which will not be repeated here.

[0099] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining the structural hierarchy of a viewing disk region, characterized in that, The method includes: The first region of the user's eye, including the optic disc area, is scanned line by line to obtain OCT volume data; Using the center point of the first region as the star-shaped sampling center, star-shaped sampling is performed on the OCT volume data to obtain a first number of first BScan two-dimensional cross-sectional image data. The initial center point of the visual disc region is determined based on each first BScan two-dimensional cross-sectional image data; wherein the initial center point is determined based on the centroid of the first Bruch membrane opening region determined by each first BScan two-dimensional cross-sectional image data. Using the initial center point as the star-shaped sampling center, the OCT volume data is sampled again in a star shape to obtain a second number of second BScan two-dimensional cross-sectional image data; Based on each second BScan two-dimensional cross-sectional image data, the structural hierarchy of the visual disc region is determined.

2. The method according to claim 1, characterized in that, The steps for determining the initial center point of the visual disc region based on each first BScan two-dimensional cross-sectional image data include: Semantic segmentation is performed on each first BScan two-dimensional cross-sectional image data to determine the first visual disk structure layering result of each first BScan two-dimensional cross-sectional image data; Based on the physical distance between the center point of the first region and the four vertices of the first region, boundary filling is performed on the layering result of each first visual disk structure. The layering result of each first visual disk structure after filling is converted into the first polar coordinate layering result in the polar coordinate system, and the first polar coordinate layering result is converted into the first rectangular coordinate layering result in the rectangular coordinate system. The position of the first region in the first rectangular coordinate layering result is determined based on the center point of the first region. Based on the location of the first region, the first layering result corresponding to the first region is extracted from the first rectangular coordinate layering result; The first Bruch membrane opening region is determined based on the first layering result, and the centroid of the first Bruch membrane opening region is determined as the initial center point of the visual disc region.

3. The method according to claim 2, characterized in that, The steps for filling the boundaries of each first visual disk structure layering result based on the physical distance between the center point of the first region and the four vertices of the first region include: Calculate the first physical distance between the center point of the first region and each of the four vertices of the first region; The maximum distance among multiple first physical distances is used as the first radius of the first circumcircle. Based on the first radius, the boundary of each first visual disc structure layering result is filled so that the range covered by each first visual disc structure layering result after filling corresponds to the diameter of the first circumcircle.

4. The method according to claim 1, characterized in that, The step of determining the structural hierarchy of the optic disc region based on each second BScan two-dimensional section image data includes: Semantic segmentation is performed on each second BScan two-dimensional section image data to determine the second visual disk structure layering result of each second BScan two-dimensional section image data; Based on the physical distance between the initial center point and the four vertices of the first region, boundary filling is performed on the layering result of each second visual disk structure. The layering result of each second view disk structure after filling is converted into the second polar coordinate layering result in the polar coordinate system, and the second polar coordinate layering result is converted into the second rectangular coordinate layering result in the rectangular coordinate system. The position of the first region in the second region of the second rectangular coordinate layering result is determined based on the initial center point; Based on the location of the second region, the second layering result corresponding to the first region is extracted from the second rectangular coordinate layering result; The structural hierarchy of the visual disc region is determined based on the second layering result.

5. The method according to claim 4, characterized in that, The step of filling the boundary of each second visual disk structure layering result based on the physical distance between the initial center point and the four vertices of the first region includes: Calculate the second physical distances between the initial center point and the four vertices of the first region; The maximum distance among multiple second physical distances is used as the second radius of the second circumcircle. Based on the second radius, the boundary of each second visual disk structure layering result is filled so that the range covered by each second visual disk structure layering result after filling corresponds to the diameter of the second circumcircle.

6. The method according to claim 4, characterized in that, The method further includes: The second Bruch membrane opening region is determined based on the second layering result; The centroid of the opening region of the second Bruch membrane is determined as the target center point of the visual disc region.

7. The method according to claim 1, characterized in that, The second quantity is greater than the first quantity; each first BScan two-dimensional cross-sectional image data is sampled at a first interval angle; each second BScan two-dimensional cross-sectional image data is sampled at a second interval angle; wherein, the first interval angle is greater than the second interval angle.

8. A device for determining the structural hierarchy of a viewing disc region, characterized in that, The device includes: The acquisition module is used to scan the first region of the user's eye, including the optic disc region, line by line to acquire OCT volume data. The first sampling module is used to perform star-shaped sampling on the OCT volume data with the center point of the first region as the star-shaped sampling center to obtain a first number of first BScan two-dimensional cross-sectional image data. The first determining module is used to determine the initial center point of the visual disc region based on each first BScan two-dimensional cross-sectional image data; wherein the initial center point is determined based on the centroid of the first Bruch membrane opening region determined by each first BScan two-dimensional cross-sectional image data. The second sampling module is used to perform star-shaped sampling on the OCT volume data again with the initial center point as the star-shaped sampling center to obtain a second number of second BScan two-dimensional cross-sectional image data. The second determining module is used to determine the structural hierarchy of the visual disc region based on each of the second BScan two-dimensional cross-sectional image data.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing machine-executable instructions that can be executed by the processor, the processor executing the machine-executable instructions to implement the disc region structure hierarchy determination method according to any one of claims 1-7.

10. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores machine-executable instructions that, when invoked and executed by a processor, cause the processor to implement the method for determining the visual disc region structure hierarchy as described in any one of claims 1-7.

Images