CN113643184B - Optical coherence tomography-based fundus blood vessel display method, system and medium - Google Patents
Optical coherence tomography-based fundus blood vessel display method, system and medium Download PDFInfo
- Publication number
- CN113643184B CN113643184B CN202111206945.5A CN202111206945A CN113643184B CN 113643184 B CN113643184 B CN 113643184B CN 202111206945 A CN202111206945 A CN 202111206945A CN 113643184 B CN113643184 B CN 113643184B
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- image
- layered
- images
- octa
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
Abstract
The invention discloses a method, a system and a medium for displaying fundus blood vessels based on optical coherence tomography, wherein the method comprises the following steps: acquiring OCTA images of a plurality of visual fields; determining a video disc area of each OCTA image, and performing layering processing on each OCTA image according to the video disc area to obtain a plurality of layered blood vessel images; selecting a first layered blood vessel image positioned in a preset layer of each OCTA image, extracting blood vessel characteristics of each first layered blood vessel image, and performing image splicing on the first layered blood vessel image according to the blood vessel characteristics to obtain a complete layered blood vessel image of the preset layer; and carrying out image splicing on the layered blood vessel image of each layer of each OCTA image according to the complete layered blood vessel image of the preset layer to obtain and display the complete layered blood vessel image of each layer. The invention can completely display the blood vessel images of all cell layers of the whole fundus of the patient, is beneficial to a doctor to quickly determine the illness state of the patient, and can be widely applied to the technical field of fundus image processing.
Description
Technical Field
The invention relates to the technical field of fundus image processing, in particular to a fundus blood vessel display method, a fundus blood vessel display system and a fundus blood vessel display medium based on optical coherence tomography.
Background
The traditional fundus examination is mainly observed by a doctor by directly utilizing auxiliary equipment such as a medical magnifier and the like, and an observed image cannot be reserved, so that follow-up consultation is not facilitated, and the development state of the patient is not grasped. In response to this situation, fundus cameras have been introduced on the market, and the acquisition of fundus images by the fundus cameras using an auxiliary light source is completed. However, the optical image collected by the fundus camera overlaps the blood vessels of the multilayer structure in the entire fundus, and it is not easy to analyze the specific blood vessels of the multilayer structure in the fundus, which makes it difficult to analyze the condition of the patient.
In view of this, an OCT (Optical Coherence Tomography) scanning system has been further introduced in the market, and tomographic scanning of the fundus in the depth direction can be realized. With the development of OCT technology, an OCTA (Optical Coherence Tomography) technology is more available on the market, and imaging of fundus blood vessels can be realized. However, the imaging field of view of the OCTA scanning system is limited, and in practical application, most of the blood vessels in the fundus lesion region of the patient are displayed, and usually, a doctor determines the approximate position of the lesion and then acquires an OCTA image, so that the whole process is complicated and much effort of the doctor is required. However, even in this case, the acquired oca image cannot simultaneously display all the fundus blood vessels, which is not favorable for the doctor to analyze and judge the patient's condition.
Disclosure of Invention
The present invention aims to solve at least to some extent one of the technical problems existing in the prior art.
Therefore, an object of the embodiments of the present invention is to provide a method for displaying fundus blood vessels based on optical coherence tomography, which is beneficial for a doctor to quickly determine the condition of a patient, does not need the doctor to judge a lesion area in advance, is also convenient for the doctor to perform a comprehensive examination on the fundus blood vessels of the patient, and reduces the risks of missed examination and false examination.
Another object of an embodiment of the present invention is to provide a fundus blood vessel display system based on optical coherence tomography.
In order to achieve the technical purpose, the technical scheme adopted by the embodiment of the invention comprises the following steps:
in one aspect, an embodiment of the present invention provides a fundus blood vessel display method based on optical coherence tomography, including the following steps:
acquiring OCTA images of a plurality of visual fields, wherein the plurality of OCTA images cover the complete fundus and an overlapping area exists between the adjacent OCTA images;
determining a video disc area of each OCTA image, and performing layering processing on each OCTA image according to the video disc area to obtain a plurality of layered blood vessel images;
selecting a first layered blood vessel image positioned in a preset layer of each OCTA image from the plurality of layered blood vessel images, extracting blood vessel characteristics of each first layered blood vessel image, and performing image splicing on the first layered blood vessel image through a gradient descent algorithm according to the blood vessel characteristics to obtain a complete layered blood vessel image of the preset layer;
and carrying out image splicing on the layered blood vessel image of each layer of the OCTA images according to the complete layered blood vessel image of the preset layer to obtain the complete layered blood vessel image of each layer, and further displaying the complete layered blood vessel image of each layer.
Further, in an embodiment of the present invention, the step of acquiring the OCTA images of the plurality of fields of view specifically includes:
establishing a pupil positioning map library, wherein the pupil positioning map library comprises a plurality of groups of pupil positioning map groups, the plurality of groups of pupil positioning map groups are respectively specific to a plurality of different types of people, each pupil positioning map group comprises a plurality of pupil positioning images corresponding to different visual angles, and the visual angles are consistent with the visual fields corresponding to the OCTA images;
selecting a corresponding first pupil positioning map group from the pupil positioning map library according to the type of the crowd to which the detected person belongs;
acquiring a pupil image to be detected of a person to be detected;
matching and inquiring the first pupil positioning map group according to the pupil image to be detected, and selecting a plurality of first pupil positioning images with matching degrees exceeding a preset first threshold value;
and finishing the acquisition of the OCTA image according to the corresponding visual angle of each first pupil positioning image.
Further, in an embodiment of the present invention, the step of determining a optic disc region of each of the oca images, and performing a layering process on each of the oca images according to the optic disc region to obtain a plurality of layered blood vessel images specifically includes:
inputting the OCTA images into a pre-trained optic disc area recognition model for recognition, and determining the optic disc area of each OCTA image;
determining a first gray average value of the optic disc area, and establishing a vertical gray gradient image of the OCTA image by taking the first gray average value as a reference;
determining a plurality of gray scale boundaries in the vertical gray scale gradient image by a shortest path algorithm;
determining a plurality of cell layers according to the gray boundary, and further extracting layered blood vessel images of the cell layers;
wherein the cell layer comprises a vitreoretinal junction layer, a superficial retinal vascular layer, a deep retinal vascular layer, an outer retinal avascular layer and a choroidal capillary layer.
Further, in one embodiment of the present invention, the vertical gray scale gradient image is calculated according to the following formula:
wherein d (x, y) represents the gray value of a pixel point (x, y) in the vertical gray gradient image, I (x, y) represents the gray value of the pixel point (x, y) in the OCTA image, and μ represents the first gray average value;
the shortest path algorithm determines the gray boundaries in the vertical gray gradient image according to the following equation:
wherein, P (x, y) is shown inLength of shortest path between pixel point and pixel point (x, y) on the gray scale boundary, c (x, y) represents weight of pixel point (x, y), ω1Representing a gradient weight parameter, ω2Representing a gray-scale weight parameter, c0Representing the weight correction parameters.
Further, in an embodiment of the present invention, the step of extracting a blood vessel feature of each first hierarchical blood vessel image, and further performing image stitching on the first hierarchical blood vessel image according to the blood vessel feature by using a gradient descent algorithm to obtain a complete hierarchical blood vessel image of the preset layer specifically includes:
performing Gaussian filtering processing on each first layered blood vessel image to obtain a plurality of second layered blood vessel images subjected to denoising;
selecting two adjacent second layered blood vessel images as a first image to be spliced and a second image to be spliced;
performing local threshold segmentation processing on the first image to be spliced and the second image to be spliced, extracting a first blood vessel characteristic region of the first image to be spliced and a second blood vessel characteristic region of the second image to be spliced, determining a first blood vessel contour according to the first blood vessel characteristic region, and determining a second blood vessel contour according to the second blood vessel characteristic region;
determining one of the first blood vessel contour and the second blood vessel contour with more pixel points as a reference image and the other one as a moving image, and optimizing the pixel point distance between the reference image and the moving image through a gradient descent algorithm until the pixel point distance is minimum to obtain an optimal transformation matrix of the moving image;
performing image splicing on the first image to be spliced and the second image to be spliced according to the optimal transformation matrix to obtain a local layered vascular image;
and selecting a second layered blood vessel image adjacent to the local layered blood vessel image as a third image to be spliced, and continuously splicing until a complete layered blood vessel image is obtained.
Further, in an embodiment of the present invention, the optimal transformation matrix is optimized by the following objective function:
wherein F (t) represents the pixel distance, R1(x, y) denotes the reference map, L (x, y; t) denotes a transformation matrix of the movement map, R2[L(x,y;t)]Representing the motion map after transformation by a transformation matrix L (x, y; t), t1、t2、t3、t4、t5And t6Are all the parameters to be optimized of the transformation matrix L (x, y; t);
the gradient descent algorithm is iteratively optimized by:
wherein k represents the number of iterations and k is greater than or equal to 0, t(k)Represents the kth iteration to obtain the parameter to be optimized, t(k+1)Represents the parameter to be optimized obtained by the (k + 1) th iteration, alpha represents the iteration step length, and d(k)Denotes the direction of negative gradient, F(k)And representing the pixel point distance obtained by the k iteration.
Further, in an embodiment of the present invention, the step of image stitching the layered blood vessel images of each layer of the oca images according to the complete layered blood vessel image of the preset layer specifically includes:
carrying out coordinate calibration on each first layered blood vessel image according to the complete layered blood vessel image of the preset layer;
carrying out coordinate calibration on layered blood vessel images of other layers according to the coordinate calibration result of each first layered blood vessel image, wherein the other layers are cell layers except the preset layer in the OCAT image;
and carrying out image splicing on the layered blood vessel images of other layers according to the coordinate calibration result of the layered blood vessel images of other layers.
In another aspect, an embodiment of the present invention provides a fundus blood vessel display system based on optical coherence tomography, including:
the system comprises an OCTA image acquisition module, a video acquisition module and a video acquisition module, wherein the OCTA image acquisition module is used for acquiring OCTA images of multiple visual fields, the multiple OCTA images cover the complete fundus, and an overlapping area exists between the adjacent OCTA images;
the layered processing module is used for determining a optic disc area of each OCTA image and performing layered processing on each OCTA image according to the optic disc area to obtain a plurality of layered blood vessel images;
the characteristic extraction and image splicing module is used for selecting a first layered blood vessel image positioned on a preset layer of each OCTA image from the layered blood vessel images, extracting blood vessel characteristics of each first layered blood vessel image, and further performing image splicing on the first layered blood vessel image through a gradient descent algorithm according to the blood vessel characteristics to obtain a complete layered blood vessel image of the preset layer;
and the image splicing and displaying module is used for carrying out image splicing on the layered blood vessel image of each layer of the OCTA images according to the complete layered blood vessel image of the preset layer to obtain the complete layered blood vessel image of each layer, and further displaying the complete layered blood vessel image of each layer.
In another aspect, an embodiment of the present invention provides a fundus blood vessel display apparatus based on optical coherence tomography, including:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one program causes the at least one processor to implement the optical coherence tomography-based fundus blood vessel visualization method described above.
In another aspect, an embodiment of the present invention further provides a computer-readable storage medium, in which a processor-executable program is stored, and the processor-executable program is configured to execute the foregoing optical coherence tomography-based fundus blood vessel displaying method when executed by a processor.
Advantages and benefits of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention:
according to the embodiment of the invention, a plurality of OCTA images with different visual fields are obtained, then the optic disc area of each OCTA image is confirmed, each OCTA image is subjected to layering processing according to the optic disc area to obtain a plurality of layered blood vessel images, then the first layered blood vessel image positioned on the preset layer of each OCTA image is selected and the blood vessel characteristics of the first layered blood vessel image are extracted, image splicing is carried out according to the blood vessel characteristics by using a gradient descent algorithm to obtain the complete layered blood vessel image of the preset layer, so that the splicing of the layered blood vessel images of other layers can be completed according to the splicing result of the preset layer, and the complete layered blood vessel image of each layer is obtained and displayed. According to the embodiment of the invention, the OCTA image is layered according to the optic disc area with more concentrated visual nerves, so that the layering accuracy is improved; by extracting the blood vessel characteristics and utilizing the gradient descent algorithm to splice adjacent layered blood vessel images, the accuracy and the integrity of image splicing are improved; through layering and concatenation processing to the OCTA image, can show the vascular image on each cell layer of the whole eye ground of patient completely, compare in prior art and only carry out local eye ground blood vessel show, be favorable to the doctor to confirm the patient's state of an illness fast, need not the doctor and carry out the regional judgement of focus in advance, in addition, once only show each layer of blood vessel of whole eye ground, the doctor of also being convenient for carries out comprehensive inspection to patient's eye ground blood vessel, has reduced the risk of lou examining and wrong detection.
Drawings
In order to more clearly illustrate the technical solution in the embodiment of the present invention, the following description is made on the drawings required to be used in the embodiment of the present invention, and it should be understood that the drawings in the following description are only for convenience and clarity of describing some embodiments in the technical solution of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart illustrating steps of a fundus blood vessel displaying method based on optical coherence tomography according to an embodiment of the present invention;
FIG. 2 is a schematic view of the cell layers of an OCTA image provided in accordance with an embodiment of the present invention;
FIG. 3A is a schematic diagram of a reference map provided in accordance with an embodiment of the present invention;
FIG. 3B is a schematic diagram of a moving picture according to an embodiment of the present invention;
FIG. 3C is a schematic diagram of a partially layered vascular image provided in accordance with an embodiment of the present invention;
fig. 4 is a block diagram of a fundus blood vessel display system based on optical coherence tomography according to an embodiment of the present invention;
fig. 5 is a structural block diagram of a fundus blood vessel display device based on optical coherence tomography according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided only for convenience of illustration, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art.
In the description of the present invention, the meaning of a plurality is two or more, if there is a description to the first and the second for the purpose of distinguishing technical features, it is not understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or implicitly indicating the precedence of the indicated technical features. Furthermore, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art.
Referring to fig. 1, an embodiment of the present invention provides a fundus blood vessel display method based on optical coherence tomography, specifically including the following steps:
s101, acquiring OCTA images of a plurality of visual fields, wherein the plurality of OCTA images cover the complete eyeground, and adjacent OCTA images have overlapping regions.
Specifically, the OCTA image may be obtained by an OCTA scanning system, and the acquisition of the OCTA images of a plurality of different fields of view may be completed by adjusting the field of view scanned by the OCTA scanning system. In order to ensure that the acquired oca images can cover the entire fundus, a certain overlap area needs to exist between the plurality of oca images. Step S101 specifically includes the following steps:
s1011, constructing a pupil positioning map library, wherein the pupil positioning map library comprises a plurality of groups of pupil positioning map groups, the groups of pupil positioning map groups are respectively specific to a plurality of different crowd types, each pupil positioning map group comprises a plurality of pupil positioning images corresponding to different visual angles, and the visual angles are consistent with the visual fields corresponding to the OCTA images;
s1012, selecting a corresponding first pupil positioning map group from a pupil positioning map library according to the type of the crowd to which the detected person belongs;
s1013, acquiring a pupil image to be detected of the detected person;
s1014, performing matching query in the first pupil positioning map group according to the pupil image to be detected, and selecting a plurality of first pupil positioning images with matching degrees exceeding a preset first threshold;
and S1015, completing the acquisition of the OCTA images according to the corresponding visual angles of the first pupil positioning images.
Specifically, the embodiment of the invention collects the OCTA images according to the pupil positions of the tested person, so that the pupil sight line change is within the preset sight line change allowable range when a plurality of OCTA images are collected.
When a plurality of OCTA images are collected, the pupil positions and the sight lines of the detected person need to be kept unchanged as much as possible, so that the collected OCTA images are prevented from being changed greatly due to the rotation of eyeballs, and the layered blood vessel images cannot be spliced effectively. However, in actual operation, although the fixation lamp or fixation mark may be used to keep the attention of the person to be tested, the situation that the line of sight of the person to be tested is greatly deviated still exists. The embodiment of the invention can directly judge whether the pupil or the sight line has deviation by acquiring the pupil position, if the pupil or the sight line has deviation, scanning can be temporarily stopped, and acquisition is carried out when the pupil or the sight line returns to the acquisition range. The method can overcome the defects of the traditional manual operation mode, and can ensure the similarity of the overlapped areas of the acquired OCTA images as far as possible, thereby facilitating the subsequent splicing.
The pupil position of the pupil can be determined in many ways through a binocular vision system, but the binocular vision system is difficult to install and is difficult to combine with an OCTA scanning system; the surface layer of the eyeball can also be scanned by using the OCTA scanning system so as to determine the direction of the sight line, but the loss of the OCTA scanning system is caused, and the cost is not favorably saved. In the embodiment of the invention, the image acquisition device is directly used for acquiring the pupil image to be detected by virtue of the light path of the OCTA scanning system, so that the acquired pupil image to be detected is also changed when the visual field acquired by the OCTA scanning system is changed, therefore, the pupil positioning image can be determined according to the state of each OCTA scanning system in different visual fields, and a plurality of pupil positioning images can correspond to the standard images of the OCTA scanning system in the process of acquiring the OCTA images in the plurality of visual fields. When OCTA image acquisition is actually carried out, a certain visual field is determined, then a corresponding pupil positioning image is selected according to the visual field, and only when the matching degree of the acquired pupil image to be detected and the pupil positioning image reaches a certain threshold value, the OCTA scanning system is controlled to carry out OCTA image acquisition. Through continuously changing the visual field and then selecting the corresponding pupil positioning image for matching, the similarity of the acquired OCTA images is higher, so that the subsequent splicing can be completed.
It will be appreciated that there may be differences in pupil characteristics between different populations and, therefore, corresponding sets of pupil maps may be determined for different types of populations. When determining that OCTA image acquisition is needed, a doctor needs to select a pupil positioning map group according to the pupil characteristics of a detected person so that an OCTA scanning system can acquire effective data later.
S102, determining a video disc area of each OCTA image, and performing layering processing on each OCTA image according to the video disc area to obtain a plurality of layered blood vessel images.
Specifically, when the OCTA image is layered, the boundary of each cell layer needs to be determined, and then layered extraction is performed. In the embodiment of the present invention, the optic disc region of the OCTA image is extracted separately, and the surrounding cell layers are layered according to the optic disc region, so that the boundary of the main cell layer for disease diagnosis can be obtained, as shown in fig. 2, which is a schematic diagram of each cell layer of the OCTA image provided in the embodiment of the present invention, wherein 10 represents a choroidal capillary vessel layer, 20 represents a deep retinal vessel layer, 30 represents a superficial retinal vessel layer, 40 represents an outer retinal avascular layer, and 50 represents a vitreoretinal boundary layer. Step S102 specifically includes the following steps:
s1021, inputting the OCTA images into a pre-trained optic disc area recognition model for recognition, and determining optic disc areas of the OCTA images;
s1022, determining a first gray average value of the optic disc area, and establishing a vertical gray gradient image of the OCTA image by taking the first gray average value as a reference;
s1023, determining a plurality of gray scale boundaries in the vertical gray scale gradient image through a shortest path algorithm;
s1024, determining a plurality of cell layers according to the gray boundary, and further extracting layered blood vessel images of the cell layers;
wherein the cell layer comprises vitreoretinal interface layer, superficial retinal vascular layer, deep retinal vascular layer, outer retinal avascular layer and choroidal capillary layer.
Specifically, the optic disc region recognition model can be obtained through a general neural network training, and the specific neural network model structure and the training process are not repeated herein. Since the optic disc region is a region with concentrated visual nerves and relatively high brightness in the OCTA image, a vertical gray gradient image of the OCTA image can be established according to the gray average value of the optic disc region.
As a further alternative, the vertical gray-scale gradient image is calculated according to the following formula:
wherein d (x, y) represents the gray value of the pixel point (x, y) in the vertical gray gradient image, I (x, y) represents the gray value of the pixel point (x, y) in the OCTA image, and mu represents the first gray average value;
the shortest path algorithm determines the gray boundaries in the vertical gray gradient image according to:
wherein, P (x, y) represents the length of the shortest path between the pixel point on the gray scale boundary and the pixel point (x, y), c (x, y) represents the weight of the pixel point (x, y), ω1Representing a gradient weight parameter, ω2Representing a gray-scale weight parameter, c0Representing the weight correction parameters.
In the embodiment of the invention, P (x-1, y-1) represents the length of the shortest path between a pixel point on a gray boundary and a pixel point (x-1, y-1), when an algorithm is transmitted from the pixel point (x-1, y-1) to the pixel point (x, y), the accumulated cost (x-1, y-1) of the previous pixel point is replaced by the accumulated loss of a short curve, and the short curve is obtained by backtracking the preset length from the current node (x, y) to the previous node (x-1, y-1). In the embodiment of the invention, when the curve sudden change occurs in the gray scale boundary, the accumulated cost between two adjacent inflection points is not erroneously smaller than the expected result, so that the determined gray scale boundary is more accurate.
Specifically, after the vertical gray gradient image is obtained, a plurality of gray boundaries, which are cell layer boundaries, can be determined through a shortest path algorithm, so that a plurality of cell layers can be determined, and the layered blood vessel images of each cell layer are extracted from the original OCTA image.
S103, selecting a first layered blood vessel image positioned on a preset layer of each OCTA image from the plurality of layered blood vessel images, extracting blood vessel characteristics of each first layered blood vessel image, and performing image splicing on the first layered blood vessel image through a gradient descent algorithm according to the blood vessel characteristics to obtain a complete layered blood vessel image of the preset layer.
Specifically, in the embodiment of the present invention, when acquiring the OCTA images, the overlap areas exist among the plurality of OCTA images, and therefore, the corresponding overlap area also necessarily exists in the layered blood vessel image of each layer, and then the overlap areas of adjacent layered blood vessel images necessarily have the same image characteristics, and the image characteristics can be used to complete the stitching of the plurality of layered blood vessel images of any layer in the fundus. The embodiment of the invention needs to display the complete fundus blood vessels, so the blood vessel characteristics are adopted as the image characteristics to complete the splicing.
It should be appreciated that in the embodiment of the present invention, the first layered blood vessel image of the preset layer needs to include the blood vessel feature, and therefore, the selection of the outer retinal avascular layer needs to be avoided. In the embodiment of the invention, the superficial retinal vascular layer with relatively obvious vascular characteristics is used as the preset layer, so that the calculation amount can be reduced on one hand, and the accuracy of vascular characteristic extraction can be improved on the other hand. It will be appreciated that the splicing of the outer retinal avascular layer may be accomplished using the result of splicing of predetermined layers, and although the outer retinal avascular layer typically does not contain vascular features, it is of high importance that once vascular features are found in the layer, which indicates vascular proliferation, further investigation or treatment is required.
As a further optional implementation manner, the method includes the steps of extracting blood vessel features of each first hierarchical blood vessel image, and further performing image splicing on the first hierarchical blood vessel images according to the blood vessel features through a gradient descent algorithm to obtain a complete hierarchical blood vessel image of a preset layer, and specifically includes:
a1, carrying out Gaussian filtering processing on each first hierarchical blood vessel image to obtain a plurality of second hierarchical blood vessel images subjected to denoising;
a2, selecting two adjacent second layered blood vessel images as a first image to be spliced and a second image to be spliced;
a3, performing local threshold segmentation processing on the first image to be spliced and the second image to be spliced, extracting a first blood vessel characteristic region of the first image to be spliced and a second blood vessel characteristic region of the second image to be spliced, determining a first blood vessel contour according to the first blood vessel characteristic region, and determining a second blood vessel contour according to the second blood vessel characteristic region;
a4, determining one of the first blood vessel contour and the second blood vessel contour with more pixel points as a reference image and the other one as a moving image, and optimizing the distance of the pixel points between the reference image and the moving image through a gradient descent algorithm until the distance of the pixel points is minimum to obtain an optimal transformation matrix of the moving image;
a5, carrying out image stitching on the first image to be stitched and the second image to be stitched according to the optimal transformation matrix to obtain a local layered blood vessel image;
and A6, selecting a second layered blood vessel image adjacent to the local layered blood vessel image as a third image to be spliced, and continuously splicing until a complete layered blood vessel image is obtained.
Specifically, the OCT reflectance signal is relatively weak in the out-of-focus region of the retina, and therefore the OCTA decorrelation signal reflecting the change of the OCT reflectance signal also decreases in the out-of-focus region, and in order to correct the brightness unevenness, the embodiment of the present invention creates a brightness offset field through gaussian filtering, and performs brightness correction on the first hierarchical blood vessel image by using the brightness offset field.
The vessel characteristics of the images to be spliced can be obvious through local threshold segmentation, and the local threshold segmentation process comprises the following steps: determining a gray level mean value and a standard deviation of each pixel point of the image to be spliced in a preset neighborhood, and determining a first characteristic threshold value of each pixel point according to the gray level mean value and the standard deviation; and performing threshold division on pixel points of the image to be spliced according to the first characteristic threshold, setting the gray value of the pixel point with the gray level larger than the first characteristic threshold to be 255, and setting the gray value of the pixel point with the gray level smaller than the first characteristic threshold to be 0, so that a binary image with obvious vessel characteristic division can be obtained.
In some optional embodiments, the gray average of the pixel points in the image to be stitched in the preset neighborhood may be calculated by the following formula:
wherein m (x, y) represents the gray average value of the pixel point (x, y) in the r neighborhood, r represents the preset neighborhood radius, r is more than or equal to 1, g (i, j) represents the gray value of the pixel point (i, j), and (i, j) represents the pixel point in the r neighborhood of the pixel point (x, y);
the standard deviation of the pixel points in the image to be spliced in the preset neighborhood can be calculated by the following formula:
wherein s (x, y) represents the standard deviation of the pixel (x, y) in the r neighborhood, g (x, y) represents the gray value of the pixel (x, y), and N represents the number of the pixels in the r neighborhood;
the first characteristic threshold may be calculated by:
wherein, T (x, y) represents a first characteristic threshold value of the pixel point (x, y), and q represents a preset correction value.
After a binary image with obvious vessel characteristic segmentation is obtained through local threshold segmentation, a vessel characteristic region is extracted, so that the vessel contour can be determined. When actually performing the splicing, it is necessary to select a blood vessel region that is relatively unique as a blood vessel feature region as much as possible, for example: vessel bifurcation, vessel intersection, etc., can increase the accuracy of matching. According to the original position of the blood vessel outline in the image to be spliced, the extracted blood vessel outline is placed in a zero matrix of pixel units with the length and the width respectively larger than the original image to be spliced by a preset number (such as 100 or 200), so that the interference of other irrelevant features in the image to be spliced can be eliminated during splicing. Selecting a blood vessel contour with more pixel points from the blood vessel contours of the two images to be spliced as a reference image, taking the other blood vessel contour as a moving image, minimizing the pixel point distance between the two blood vessel contours by a gradient descent algorithm to obtain an optimal transformation matrix of the moving image, and splicing the original images to be spliced by utilizing the matrix.
Further as an optional implementation, the optimal transformation matrix is obtained by optimizing the following objective function:
wherein F (t) represents the distance of pixel points, R1(x, y) denotes a reference map, L (x, y; t) denotes a transformation matrix of a motion map, R2[L(x,y;t)]Representing the motion map after transformation by a transformation matrix L (x, y; t), t1、t2、t3、t4、t5And t6Are all the parameters to be optimized of the transformation matrix L (x, y; t);
the gradient descent algorithm is iteratively optimized by:
wherein k represents the number of iterations and k is greater than or equal toAt 0, t(k)Represents the kth iteration to obtain the parameter to be optimized, t(k+1)Represents the parameter to be optimized obtained by the (k + 1) th iteration, alpha represents the iteration step length, and d(k)Denotes the direction of negative gradient, F(k)And representing the pixel point distance obtained by the k iteration.
In the embodiment of the present invention, the minimum value of the objective function needs to be solved through iterative optimization, so as to minimize the distance between the pixel points between the moving graph and the reference graph, and the specific optimization process is as follows: first, the initial values t of the parameters to be optimized of the transformation matrix L (x, y; t) are determined1 (0)、t2 (0)、t3 (0)、t4 (0)、t5 (0)And t6 (0)(ii) a Then, transforming the moving graph according to the initial transformation matrix, and solving the pixel point distance between the transformed moving graph and the reference graph; then, each parameter to be optimized is subjected to iterative processing to obtain t1 (1)、t2 (1)、t3 (1)、t4 (1)、t5 (1)And t6 (1)Transforming the moving graph according to the iterated parameters to be optimized and solving the pixel point distance between the transformed moving graph and the reference graph; and after repeating iteration for a certain number of iterations, determining the minimum value of the pixel point distance, and determining a corresponding optimal transformation matrix. The original image to be spliced can be spliced by utilizing the matrix.
Fig. 3A, fig. 3B, and fig. 3C are schematic diagrams of a reference map, a moving map, and a local layered blood vessel image provided by an embodiment of the present invention, respectively, where fig. 3A shows a blood vessel contour of the reference map, fig. 3B shows a blood vessel contour of the moving map, fig. 3C shows a local layered blood vessel image obtained by stitching images to be stitched according to an optimal transformation matrix obtained by optimization of the reference map and the moving map, and a dashed-line frame 300 in fig. 3C represents an overlapping region of two images to be stitched, it can be understood that the overlapping region and a left portion thereof are images to be stitched that include the blood vessel contour of the reference map, and the overlapping region and a right portion thereof are images to be stitched that include the blood vessel contour of the moving map.
After the first-time splicing is completed, if the layered blood vessel images are not spliced, the partially spliced blood vessel images obtained by splicing are spliced with the rest of the layered blood vessel images continuously, and the process is circulated until the complete layered blood vessel images are obtained.
It can be appreciated that in the conventional image processing method, similar images are generally matched based on template matching, and the template matching only performs translation operation on a template map and cannot match images with angular offsets.
And S104, carrying out image splicing on the layered blood vessel image of each layer of each OCTA image according to the complete layered blood vessel image of the preset layer to obtain the complete layered blood vessel image of each layer, and further displaying the complete layered blood vessel image of each layer.
Specifically, since a single OCTA image is acquired at one time, the layered blood vessel images of the cell layers of the fundus obtained by performing layered processing on the same OCTA image inevitably have a corresponding relationship, and as long as the splicing of the plurality of layered blood vessel images of the preset layer can be completed, the splicing of the plurality of layered blood vessel images of other layers can also be completed by using the splicing result of the preset layer. For example, the layered blood vessel images of each layer may be coordinated, so that the corresponding positions may be directly determined in the other layered blood vessel image according to the correspondence between the two layered blood vessel images.
As a further optional implementation manner, the step of image stitching the layered blood vessel images of each layer of each OCTA image according to the complete layered blood vessel image of the preset layer specifically includes:
b1, carrying out coordinate calibration on each first layered blood vessel image according to the complete layered blood vessel image of the preset layer;
b2, carrying out coordinate calibration on layered blood vessel images of other layers according to the coordinate calibration result of each first layered blood vessel image, wherein the other layers are cell layers except a preset layer in the OCAT image;
and B3, performing image stitching on the layered blood vessel images of other layers according to the coordinate calibration result of the layered blood vessel images of other layers.
Specifically, when the layered blood vessel images of other layers are spliced, the splicing is not required to be performed according to the whole overlapping area, only one reference point in the overlapping area is used for carrying out coordinate calibration on the two spliced layered blood vessel images, then the coordinate calibration on the layered blood vessel images of other layers is completed according to the reference point, and finally, the image splicing can be directly performed according to the calibration results of the layered blood vessel images of other layers to obtain the complete layered blood vessel image of each layer.
In some optional embodiments, the spliced fundus layer complete layered blood vessel images can be displayed through a visualization platform. In order to better display each layer of complete layered blood vessel images in the visualization platform, a plurality of viewing labels can be arranged in the visualization platform, the viewing labels correspond to the complete layered blood vessel images one by one, and the viewing labels can be operated to complete the respective display of the complete layered blood vessel images. In actual diagnosis, the complete hierarchical blood vessel image is not used as a sole diagnostic basis, and diagnosis needs to be performed in combination with a CT scan image or the like.
When the complete layered blood vessel image is displayed, the blood vessel highlighted complete image after binarization processing of the complete layered blood vessel image can be displayed at the same time, although the blood vessel highlighted complete image has fewer features, a doctor can conveniently and rapidly screen the disease condition, the film reading burden of the doctor is reduced, and after the disease focus position is determined through the blood vessel highlighted complete image, the disease condition can be further analyzed by further utilizing the complete layered blood vessel image.
The method steps of the embodiments of the present invention are described above. It can be understood that the embodiment of the invention carries out layering processing on the OCTA image according to the optic disc area with more concentrated visual nerves, thereby improving the layering accuracy; by extracting the blood vessel characteristics and utilizing the gradient descent algorithm to splice adjacent layered blood vessel images, the accuracy and the integrity of image splicing are improved; through layering and concatenation processing to the OCTA image, can show the vascular image on each cell layer of the whole eye ground of patient completely, compare in prior art and only carry out local eye ground blood vessel show, be favorable to the doctor to confirm the patient's state of an illness fast, need not the doctor and carry out the regional judgement of focus in advance, in addition, once only show each layer of blood vessel of whole eye ground, the doctor of also being convenient for carries out comprehensive inspection to patient's eye ground blood vessel, has reduced the risk of lou examining and wrong detection.
Referring to fig. 4, an embodiment of the present invention provides an optical coherence tomography-based fundus blood vessel display system, including:
the OCTA image acquisition module is used for acquiring OCTA images of a plurality of visual fields, the plurality of OCTA images cover the complete fundus, and adjacent OCTA images have an overlapping area;
the layered processing module is used for determining the optic disc area of each OCTA image and performing layered processing on each OCTA image according to the optic disc area to obtain a plurality of layered blood vessel images;
the characteristic extraction and image splicing module is used for selecting a first layered blood vessel image positioned on a preset layer of each OCTA image from the plurality of layered blood vessel images, extracting blood vessel characteristics of each first layered blood vessel image, and further performing image splicing on the first layered blood vessel image through a gradient descent algorithm according to the blood vessel characteristics to obtain a complete layered blood vessel image of the preset layer;
and the image splicing and displaying module is used for carrying out image splicing on the layered blood vessel image of each layer of each OCTA image according to the complete layered blood vessel image of the preset layer to obtain the complete layered blood vessel image of each layer, and further displaying the complete layered blood vessel image of each layer.
The contents in the above method embodiments are all applicable to the present system embodiment, the functions specifically implemented by the present system embodiment are the same as those in the above method embodiment, and the beneficial effects achieved by the present system embodiment are also the same as those achieved by the above method embodiment.
Referring to fig. 5, an embodiment of the present invention provides an optical coherence tomography-based fundus blood vessel display apparatus, including:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one program causes the at least one processor to implement the method for displaying a fundus blood vessel based on optical coherence tomography.
The contents in the above method embodiments are all applicable to the present apparatus embodiment, the functions specifically implemented by the present apparatus embodiment are the same as those in the above method embodiments, and the advantageous effects achieved by the present apparatus embodiment are also the same as those achieved by the above method embodiments.
An embodiment of the present invention also provides a computer-readable storage medium in which a processor-executable program is stored, which, when executed by a processor, is configured to perform the foregoing optical coherence tomography-based fundus blood vessel visualization method.
The computer-readable storage medium of the embodiment of the invention can execute the fundus blood vessel showing method based on optical coherence tomography, can execute any combination of implementation steps of the embodiment of the method, and has corresponding functions and beneficial effects of the method.
The embodiment of the invention also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and executed by the processor to cause the computer device to perform the method illustrated in fig. 1.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the above-described functions and/or features may be integrated in a single physical device and/or software module, or one or more of the functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.
The above functions, if implemented in the form of software functional units and sold or used as a separate product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Further, the computer readable medium could even be paper or another suitable medium upon which the above described program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the foregoing description of the specification, reference to the description of "one embodiment/example," "another embodiment/example," or "certain embodiments/examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. An optical coherence tomography-based fundus blood vessel display method is characterized by comprising the following steps:
acquiring OCTA images of a plurality of visual fields, wherein the plurality of OCTA images cover the complete fundus and an overlapping area exists between the adjacent OCTA images;
determining a video disc area of each OCTA image, and performing layering processing on each OCTA image according to the video disc area to obtain a plurality of layered blood vessel images;
selecting a first layered blood vessel image positioned in a preset layer of each OCTA image from the plurality of layered blood vessel images, extracting blood vessel characteristics of each first layered blood vessel image, and performing image splicing on the first layered blood vessel image through a gradient descent algorithm according to the blood vessel characteristics to obtain a complete layered blood vessel image of the preset layer;
determining the coordinate corresponding relation between the first layered blood vessel image and layered blood vessel images of other layers, wherein the other layers are cell layers except the preset layer in the OCTA image, carrying out image splicing on the layered blood vessel images of the other layers according to the coordinate corresponding relation and the complete layered blood vessel image of the preset layer to obtain complete layered blood vessel images of the other layers, and further displaying the complete layered blood vessel image of each layer.
2. A method as claimed in claim 1, wherein the step of acquiring the OCTA images of the plurality of fields of view includes:
establishing a pupil positioning map library, wherein the pupil positioning map library comprises a plurality of groups of pupil positioning map groups, the plurality of groups of pupil positioning map groups are respectively specific to a plurality of different types of people, each pupil positioning map group comprises a plurality of pupil positioning images corresponding to different visual angles, and the visual angles are consistent with the visual fields corresponding to the OCTA images;
selecting a corresponding first pupil positioning map group from the pupil positioning map library according to the type of the crowd to which the detected person belongs;
acquiring a pupil image to be detected of a person to be detected;
matching and inquiring the first pupil positioning map group according to the pupil image to be detected, and selecting a plurality of first pupil positioning images with matching degrees exceeding a preset first threshold value;
and finishing the acquisition of the OCTA image according to the corresponding visual angle of each first pupil positioning image.
3. A method as claimed in claim 1, wherein the step of determining a optic disc area of each of the oca images and performing a layering process on each of the oca images according to the optic disc area to obtain a plurality of layered blood vessel images includes:
inputting the OCTA images into a pre-trained optic disc area recognition model for recognition, and determining the optic disc area of each OCTA image;
determining a first gray average value of the optic disc area, and establishing a vertical gray gradient image of the OCTA image by taking the first gray average value as a reference;
determining a plurality of gray scale boundaries in the vertical gray scale gradient image by a shortest path algorithm;
determining a plurality of cell layers according to the gray boundary, and further extracting layered blood vessel images of the cell layers;
wherein the cell layer comprises a vitreoretinal junction layer, a superficial retinal vascular layer, a deep retinal vascular layer, an outer retinal avascular layer and a choroidal capillary layer.
4. A fundus blood vessel displaying method based on optical coherence tomography according to claim 3, characterized in that said vertical gray gradient image is calculated according to the following formula:
wherein d (x, y) represents the gray value of a pixel point (x, y) in the vertical gray gradient image, I (x, y) represents the gray value of the pixel point (x, y) in the OCTA image, and μ represents the first gray average value;
the shortest path algorithm determines the gray boundaries in the vertical gray gradient image according to the following equation:
wherein, P (x, y) represents the length of the shortest path between the pixel point on the gray scale boundary and the pixel point (x, y), c (x, y) represents the weight of the pixel point (x, y), and ω is1Representing a gradient weight parameter, ω2Representing a gray-scale weight parameter, c0Representing the weight correction parameters.
5. An fundus blood vessel display method based on optical coherence tomography according to claim 1, wherein the step of extracting the blood vessel characteristics of each first layered blood vessel image, and further performing image stitching on the first layered blood vessel image according to the blood vessel characteristics by a gradient descent algorithm to obtain a complete layered blood vessel image of the preset layer specifically comprises:
performing Gaussian filtering processing on each first layered blood vessel image to obtain a plurality of second layered blood vessel images subjected to denoising;
selecting two adjacent second layered blood vessel images as a first image to be spliced and a second image to be spliced;
performing local threshold segmentation processing on the first image to be spliced and the second image to be spliced, extracting a first blood vessel characteristic region of the first image to be spliced and a second blood vessel characteristic region of the second image to be spliced, determining a first blood vessel contour according to the first blood vessel characteristic region, and determining a second blood vessel contour according to the second blood vessel characteristic region;
determining one of the first blood vessel contour and the second blood vessel contour with more pixel points as a reference image and the other one as a moving image, and optimizing the pixel point distance between the reference image and the moving image through a gradient descent algorithm until the pixel point distance is minimum to obtain an optimal transformation matrix of the moving image;
performing image splicing on the first image to be spliced and the second image to be spliced according to the optimal transformation matrix to obtain a local layered vascular image;
and selecting a second layered blood vessel image adjacent to the local layered blood vessel image as a third image to be spliced, and continuously splicing until a complete layered blood vessel image is obtained.
6. An optical coherence tomography-based fundus blood vessel showing method according to claim 5, wherein the optimal transformation matrix is obtained by the following objective function optimization:
wherein F (t) represents the pixel distance, R1(x, y) denotes the reference map, L (x, y; t) denotes a transformation matrix of the movement map, R2[L(x,y;t)]Representing the motion map after transformation by a transformation matrix L (x, y; t), t1、t2、t3、t4、t5And t6Are all the parameters to be optimized of the transformation matrix L (x, y; t);
the gradient descent algorithm is iteratively optimized by:
wherein k represents the number of iterations and k is greater than or equal to 0, t(k)Indicates that the kth iteration is to beOptimization parameter, t(k+1)Represents the parameter to be optimized obtained by the (k + 1) th iteration, alpha represents the iteration step length, and d(k)Denotes the direction of negative gradient, F(k)And representing the pixel point distance obtained by the k iteration.
7. A fundus blood vessel displaying method based on optical coherence tomography according to claim 1, wherein the step of image stitching the layered blood vessel images of other layers according to the coordinate correspondence and the complete layered blood vessel image of the preset layer specifically comprises:
carrying out coordinate calibration on each first layered blood vessel image according to the complete layered blood vessel image of the preset layer;
carrying out coordinate calibration on the layered blood vessel images of other layers according to the coordinate corresponding relation and the coordinate calibration result of each first layered blood vessel image;
and carrying out image splicing on the layered blood vessel images of other layers according to the coordinate calibration result of the layered blood vessel images of other layers.
8. An optical coherence tomography-based fundus blood vessel display system, comprising:
the system comprises an OCTA image acquisition module, a video acquisition module and a video acquisition module, wherein the OCTA image acquisition module is used for acquiring OCTA images of multiple visual fields, the multiple OCTA images cover the complete fundus, and an overlapping area exists between the adjacent OCTA images;
the layered processing module is used for determining a optic disc area of each OCTA image and performing layered processing on each OCTA image according to the optic disc area to obtain a plurality of layered blood vessel images;
the characteristic extraction and image splicing module is used for selecting a first layered blood vessel image positioned on a preset layer of each OCTA image from the layered blood vessel images, extracting blood vessel characteristics of each first layered blood vessel image, and further performing image splicing on the first layered blood vessel image through a gradient descent algorithm according to the blood vessel characteristics to obtain a complete layered blood vessel image of the preset layer;
and the image splicing and displaying module is used for determining the coordinate corresponding relation between the first layered blood vessel image and the layered blood vessel images of other layers, wherein the other layers are cell layers except the preset layer in the OCTA image, and performing image splicing on the layered blood vessel images of the other layers according to the coordinate corresponding relation and the complete layered blood vessel image of the preset layer to obtain the complete layered blood vessel images of the other layers, so that the complete layered blood vessel image of each layer is displayed.
9. An optical coherence tomography-based fundus blood vessel display device, comprising:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one processor may implement the optical coherence tomography-based fundus blood vessel presentation method according to any one of claims 1 to 7.
10. A computer-readable storage medium in which a processor-executable program is stored, the processor-executable program being configured to perform an optical coherence tomography-based fundus blood vessel presentation method according to any one of claims 1 to 7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111206945.5A CN113643184B (en) | 2021-10-18 | 2021-10-18 | Optical coherence tomography-based fundus blood vessel display method, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111206945.5A CN113643184B (en) | 2021-10-18 | 2021-10-18 | Optical coherence tomography-based fundus blood vessel display method, system and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113643184A CN113643184A (en) | 2021-11-12 |
| CN113643184B true CN113643184B (en) | 2022-02-18 |
Family
ID=78427198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111206945.5A Active CN113643184B (en) | 2021-10-18 | 2021-10-18 | Optical coherence tomography-based fundus blood vessel display method, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113643184B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958412A (en) * | 2023-06-16 | 2023-10-27 | 北京至真互联网技术有限公司 | OCT image-based three-dimensional eye reconstruction method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016167001A1 (en) * | 2015-04-14 | 2016-10-20 | 株式会社トプコン | Ophthalmic image display device and ophthalmic imaging device |
| US20180064336A1 (en) * | 2016-09-07 | 2018-03-08 | Nidek Co., Ltd. | Ophthalmic analysis apparatus and ophthalmic analysis method |
| CN108961261A (en) * | 2018-03-14 | 2018-12-07 | 中南大学 | A kind of optic disk region OCT image Hierarchical Segmentation method based on spatial continuity constraint |
| CN111242850A (en) * | 2020-03-06 | 2020-06-05 | 中国科学院宁波工业技术研究院慈溪生物医学工程研究所 | Wide-area fundus optical coherence blood flow imaging resolution improving method |
| CN111436905A (en) * | 2020-04-03 | 2020-07-24 | 北京图湃影像科技有限公司 | Optical coherence tomography angiography method and device |
-
2021
- 2021-10-18 CN CN202111206945.5A patent/CN113643184B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016167001A1 (en) * | 2015-04-14 | 2016-10-20 | 株式会社トプコン | Ophthalmic image display device and ophthalmic imaging device |
| US20180064336A1 (en) * | 2016-09-07 | 2018-03-08 | Nidek Co., Ltd. | Ophthalmic analysis apparatus and ophthalmic analysis method |
| CN108961261A (en) * | 2018-03-14 | 2018-12-07 | 中南大学 | A kind of optic disk region OCT image Hierarchical Segmentation method based on spatial continuity constraint |
| CN111242850A (en) * | 2020-03-06 | 2020-06-05 | 中国科学院宁波工业技术研究院慈溪生物医学工程研究所 | Wide-area fundus optical coherence blood flow imaging resolution improving method |
| CN111436905A (en) * | 2020-04-03 | 2020-07-24 | 北京图湃影像科技有限公司 | Optical coherence tomography angiography method and device |
Non-Patent Citations (1)
| Title |
|---|
| 光学相干断层扫描血管成像在眼科中的应用;段如月等;《中国现代医药杂志》;20180325(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113643184A (en) | 2021-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Can et al. | Rapid automated tracing and feature extraction from retinal fundus images using direct exploratory algorithms | |
| Abràmoff et al. | Retinal imaging and image analysis | |
| US20210390696A1 (en) | Medical image processing apparatus, medical image processing method and computer-readable storage medium | |
| US20100061601A1 (en) | Optimal registration of multiple deformed images using a physical model of the imaging distortion | |
| Hernandez-Mier et al. | Fast construction of panoramic images for cystoscopic exploration | |
| Kolar et al. | Hybrid retinal image registration using phase correlation | |
| Abramoff et al. | The automatic detection of the optic disc location in retinal images using optic disc location regression | |
| CN109124662B (en) | Rib center line detection device and method | |
| Groves et al. | Automatic segmentation of the carotid artery and internal jugular vein from 2D ultrasound images for 3D vascular reconstruction | |
| CN112164043A (en) | Method and system for splicing multiple fundus images | |
| US11830193B2 (en) | Recognition method of intracranial vascular lesions based on transfer learning | |
| CN111128382A (en) | Artificial intelligence multimode imaging analytical equipment | |
| CN113436070B (en) | Fundus image splicing method based on deep neural network | |
| CN113557714A (en) | Medical image processing apparatus, medical image processing method, and program | |
| CN113643184B (en) | Optical coherence tomography-based fundus blood vessel display method, system and medium | |
| Rivas-Villar et al. | Color fundus image registration using a learning-based domain-specific landmark detection methodology | |
| WO2013031536A1 (en) | Image analysis device for ophthalmic disease, image analysis method for ophthalmic disease, and image analysis program for ophthalmic disease | |
| CN111445575A (en) | Image reconstruction method and device of Wirisi ring, electronic device and storage medium | |
| CN114037803A (en) | Medical image three-dimensional reconstruction method and system | |
| Kolar et al. | Registration and fusion of the autofluorescent and infrared retinal images | |
| CN108510446B (en) | Method and device for superimposing retinal images | |
| Marrugo et al. | Image analysis in modern ophthalmology: from acquisition to computer assisted diagnosis and telemedicine | |
| CN112669256B (en) | Medical image segmentation and display method based on transfer learning | |
| CN110930394B (en) | Method and terminal equipment for measuring slope and pinnate angle of muscle fiber bundle line | |
| Xu et al. | Auto-adjusted 3-D optic disk viewing from low-resolution stereo fundus image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Fundus blood vessel display method, system and medium based on optical coherence tomography Effective date of registration: 20230228 Granted publication date: 20220218 Pledgee: Bank of China Limited by Share Ltd. Foshan branch Pledgor: GUANGDONG WEIREN MEDICAL TECHNOLOGY Co.,Ltd. Registration number: Y2023980033590 |