Evaluation method of retinal tissue layering thickness and storage medium

Abstract

The invention discloses a retinal tissue layering thickness evaluation method and a storage medium. The method comprises the following steps: acquiring a tissue scanning image of a retina tissue, and determining layering curves corresponding to a plurality of structural layers of the retina tissue in the tissue scanning image; determining a reference curve from the plurality of layered curves, and moving the reference curve along the arrangement direction of the plurality of structural layers to obtain a reference curve; determining a first position deviation value of the reference curve and the layering curve at a first reference point, determining a target statistical histogram according to the first position deviation value, and determining thickness characteristic data corresponding to the layering thickness of the retina tissue according to the target statistical histogram, the accuracy and the automation degree of retinal layering thickness measurement are remarkably improved, personal errors are reduced, and the accuracy and the detection efficiency of retinal tissue layering thickness detection are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and particularly relates to a method for evaluating the layered thickness of retinal tissue and a storage medium. Background Art

[0002] In medical image analysis, accurately measuring the layered thickness of retinal tissue is crucial for diagnosing and detecting various eye diseases.

[0003] In related technologies, it mainly relies on technicians to determine the position accuracy of the layered line through empirical methods. However, due to factors such as the limitations of imaging devices and individual differences among technicians, there are often problems such as large measurement errors and poor repeatability. In addition, manually analyzing a large amount of image data is time-consuming and prone to fatigue, resulting in low evaluation efficiency. Summary of the Invention

[0004] The present invention provides a method for evaluating the layered thickness of retinal tissue and a storage medium to solve the problem in related technologies that it is difficult to accurately measure the layered thickness of retinal tissue by relying on manual experience.

[0005] According to one aspect of the present invention, there is provided a method for evaluating the layered thickness of retinal tissue, including:

[0006] Obtaining a tissue scan image of retinal tissue and determining a layered curve corresponding to multiple structural layers of the retinal tissue in the tissue scan image;

[0007] Determining a reference curve from multiple layered curves, and moving the reference curve along the arrangement direction of the multiple structural layers to obtain a reference curve; wherein, the reference curve is the reference curve located at the target position after movement, and the target position is the position where the coincidence degree between the reference curve and the layered curve is the highest;

[0008] Determining a first position deviation amount between the reference curve and the layered curve at a first reference point, determining a target statistical histogram according to the first position deviation amount, and determining thickness feature data corresponding to the layered thickness of the retinal tissue according to the target statistical histogram.

[0009] According to another aspect of the present invention, there is provided an apparatus for evaluating the layered thickness of retinal tissue, including:

[0010] A layered curve determination module, configured to obtain a tissue scan image of retinal tissue and determine a layered curve corresponding to multiple structural layers of the retinal tissue in the tissue scan image;

[0011] A reference curve determination module, configured to determine a reference curve from multiple said stratified curves, and move the reference curve along the arrangement direction of multiple said structural layers to obtain a reference curve; wherein, the reference curve is the reference curve located at the target position after movement, and the target position is the position where the coincidence degree between the reference curve and the stratified curve is the highest;

[0012] A thickness feature data determination module, configured to determine a first position deviation amount between the reference curve and the stratified curve at a first reference point, determine a target statistical histogram according to the first position deviation amount, and determine thickness feature data corresponding to the retinal tissue stratification thickness according to the target statistical histogram.

[0013] According to another aspect of the present invention, there is provided an electronic device, the electronic device includes:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the evaluation method for the retinal tissue stratification thickness according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, there is provided a computer-readable storage medium, the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the evaluation method for the retinal tissue stratification thickness according to any embodiment of the present invention when executed by a processor.

[0018] The technical solution of the embodiment of the present invention can identify each structural layer by obtaining a tissue scan image of the retina tissue and determining a stratification curve corresponding to multiple structural layers of the retina tissue in the tissue scan image, and provide sufficient data support for the subsequent processing of the tissue scan image; then, a reference curve is determined from multiple stratification curves, and the reference curve is moved along the arrangement direction of the multiple structural layers to obtain a reference curve, since the reference curve is the reference curve located at the target position after movement, and the target position is the position where the coincidence degree between the reference curve and the stratification curve is the highest, which improves the accuracy and automation level of retina stratification analysis; finally, a first position deviation amount at a first reference point between the reference curve and the stratification curve is determined, a target statistical histogram is determined according to the first position deviation amount, and thickness characteristic data corresponding to the stratification thickness of the retina tissue is determined according to the target statistical histogram, which can accurately quantify the thickness characteristics of each layer of the retina tissue, solves the problem that it is difficult to accurately measure the stratification thickness of the retina tissue by relying on manual experience in the related technology, significantly improves the accuracy and automation degree of the retina stratification thickness measurement, reduces human error, and improves the accuracy and detection efficiency of the retina tissue stratification detection.

[0019] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 is a flowchart of a method for evaluating the stratification thickness of the retina tissue according to Embodiment 1 of the present invention;

[0022] Figure 2 is a flowchart of a method for evaluating the stratification thickness of the retina tissue according to Embodiment 2 of the present invention;

[0023] Figure 3 is a tissue scan image of the retina tissue before and after preprocessing of a method for evaluating the stratification thickness of the retina tissue applicable to the embodiments of the present invention;

[0024] Figure 4 is a target statistical histogram of a method for evaluating the stratification thickness of the retina tissue applicable to the embodiments of the present invention;

[0025] Figure 5 It is a schematic structural diagram of an evaluation device for the retinal tissue stratification thickness provided in Embodiment 3 of the present invention;

[0026] Figure 6 It is a schematic structural diagram of an electronic device for implementing the method for evaluating the retinal tissue stratification thickness of the embodiment of the present invention. Detailed implementation manners

[0027] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order different from those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these process, method, product or device.

[0029] It should be noted that the modifications of "one" and "multiple" mentioned in this disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless clearly specified otherwise in the context, it should be understood as "one or more".

[0030] The names of the messages or information exchanged between multiple devices in the embodiments of this disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0031] It can be understood that before using the technical solutions disclosed in the embodiments of this disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the users and the users' authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0032] For example, when receiving an active request from a user, a prompt message is sent to the user to clearly prompt that the operation requested by the user will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application program, server, or storage medium that performs the operations of the disclosed technical solution according to the prompt message.

[0033] As an optional but non-limiting implementation manner, when receiving an active request from a user, the manner of sending a prompt message to the user may be, for example, in the form of a pop-up window, and the prompt message may be presented in text in the pop-up window. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0034] It can be understood that the above process of notifying and obtaining user authorization is only illustrative and does not limit the implementation manner of the present disclosure. Other manners that comply with relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0035] It can be understood that the data involved in the present technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of corresponding laws, regulations and related provisions.

[0036] Embodiment 1

[0037] Figure 1 FIG. is a flowchart of a method for evaluating the layered thickness of retinal tissue provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of automatically evaluating the layered thickness of retinal tissue. The method can be executed by an evaluation device for the layered thickness of retinal tissue. The evaluation device for the layered thickness of retinal tissue can be implemented in the form of hardware and / or software. Optionally, it is implemented through an electronic device, and the electronic device can be a mobile terminal, a PC terminal, a server, etc.

[0038] As Figure 1 shown, the method may specifically include:

[0039] S110. Obtain a tissue scan image of retinal tissue, and determine a layered curve corresponding to a plurality of structural layers of the retinal tissue in the tissue scan image.

[0040] Among them, the tissue scan image can be understood as a high-resolution cross-sectional image of the retina obtained by an imaging technique, and the high-resolution cross-sectional image can show different structural layers of the retina. Exemplarily, the tissue scan image can be obtained by Optical Coherence Tomography (OCT). In related technologies, it has been proven that corresponding quantitative abnormalities can be found in OCT images of different retinal tissues, especially changes in thickness and the morphology of the boundary lines of each layer. The stratification curve can be understood as the curve of the boundaries of different layers in the retinal tissue. It can be understood that under normal circumstances, the retinal tissue is divided into ten layers, including the pigment epithelium layer, the rod and cone layer, and the external limiting membrane, etc., from outside to inside.

[0041] Based on the above solution, optionally, the obtaining of the tissue scan image of the retinal tissue includes: acquiring the tissue scan image of the retinal tissue through a scanning device; or, in response to an image upload operation, obtaining the tissue scan image of the retinal tissue; or, pulling the tissue scan image of the retinal tissue from a preset image database, etc., which is not specifically limited herein.

[0042] Based on the above solution, optionally, after determining the stratification curves corresponding to multiple structural layers of the retinal tissue in the tissue scan image, it further includes: respectively preprocessing the multiple stratification curves, where the preprocessing includes at least one of local smoothing filtering processing and / or Gaussian filtering processing, etc.

[0043] Specifically, the local smoothing filtering processing can be performed based on the following formula:

[0044]

[0045] where S n (x) represents the value of the nth stratification curve after local smoothing filtering processing at the sampling point x, l n (x) represents the value of the nth stratification curve of the retinal tissue at the sampling point x, k represents the size of the window of the local smoothing filter, usually an odd number, and R represents the range of all sampling points in the stratification curve.

[0046] Specifically, the Gaussian filtering processing can be performed based on the following formula:

[0047]

[0048] where G n (x) represents the value of the nth stratification curve after Gaussian filtering processing at the sampling point x; σ represents the standard deviation of the Gaussian convolution kernel, which determines the width of the Gaussian function; and R represents the range of all sampling points in the stratification curve.

[0049] An optional implementation method is to preprocess multiple said layered curves. In this process, a smoothing filter with a window size of 17 for local smoothing filtering is used, and the σ value of the Gaussian convolution kernel for Gaussian filtering is selected as 0.5. The layered curves after preprocessing are as follows Figure 3 shown. The left figure is a tissue scan image of the retinal tissue without local smoothing filtering and Gaussian filtering, and the right figure is a tissue scan image of the retinal tissue after local smoothing filtering and Gaussian filtering.

[0050] S120. Determine a reference curve from multiple said layered curves, and move the reference curve along the arrangement direction of multiple said structural layers to obtain a reference curve; wherein, the reference curve is the reference curve located at the target position after movement, and the target position is the position where the coincidence degree between the reference curve and the layered curve is the highest.

[0051] Among them, the reference curve can be understood as a curve selected from multiple layered curves as a reference standard, and the reference curve is used to compare with other layered curves to determine the first position deviation amount from other layered curves. The reference curve can be arbitrarily selected from multiple layered curves, or the outermost layered curve of the structural layer, or the innermost layered curve can be selected, which can be specifically selected according to requirements and is not limited here. The reference curve can be understood as the layered curve at the target position determined after the reference curve is moved along the arrangement direction of the retinal structural layer (usually the vertical direction). The target position can be understood as the position where the reference curve has the highest coincidence degree with the layered curve when moving to other layered curves.

[0052] Based on the above solution, optionally, the moving the reference curve along the arrangement direction of multiple said structural layers to obtain a reference curve includes: translating the reference curve along the arrangement direction of multiple said structural layers to obtain multiple translated curves; determining multiple second reference points of the layered curve, and for each said translated curve, determining the second position deviation amount between the layered curve and the translated curve at multiple said second reference points; determining the average position deviation amount of the second position deviation amounts at multiple said second reference points, and determining the translated curve with the smallest average position deviation amount as the reference curve corresponding to the reference curve.

[0053] Among them, the multiple translation curves can be understood as multiple new curves obtained by translating a reference curve, and each translation curve represents the state of the reference curve at different positions. The second reference point can be understood as a sampled data point selected on the hierarchical curve, which is used to determine the second position deviation amount between the translation curve and the hierarchical curve at the second reference point. The second position deviation amount can be understood as the difference between the translation curve and the original hierarchical curve calculated at each second reference point. The average position deviation amount can be understood as the average value of the second position deviation amounts of the determined translation curve at all second reference points, which is used to measure the coincidence degree between the translation curve and the hierarchical curve.

[0054] Based on the above solution, translating the reference curve along the arrangement direction of the multiple structural layers to obtain multiple translation curves can at least include one of the following: determining the target distance between the reference curve and the target hierarchical curve, determining the target step size according to the target distance, and translating the reference curve along the arrangement direction of the multiple structural layers according to the target step size to obtain multiple translation curves; determining the target distance between the reference curve and the target hierarchical curve, determining the target speed of the reference curve according to the target distance, and translating the reference curve along the arrangement direction of the multiple structural layers according to the target speed to obtain multiple translation curves; or, determining the target distance between the reference curve and the target hierarchical curve, dividing the target distance into a first distance and a second distance, determining the sampling time points of the reference curve within the first distance and the second distance, and translating the reference curve along the arrangement direction of the multiple structural layers to determine the translation curve at each sampling time point, so as to obtain multiple translation curves.

[0055] Among them, the target distance can be the average distance of a preset number of first reference points in the reference curve and the target hierarchical curve. The target step size can be understood as the distance that the reference curve moves each time it is translated. It can be understood that the target step sizes at multiple translation positions can be the same or different. Exemplarily, the target step size and the target distance can have a negative correlation. It can be understood that selecting an appropriate target step size can improve the efficiency of searching for the reference curve. The target speed can be understood as the distance that the reference curve moves when it is translated within each time period, and the target speed can be fixed or variable, which is not limited here. Exemplarily, when the target speed is variable, the target speed and the target distance can be negatively correlated. The first distance and the second distance can be understood as two parts into which the determined target distance is divided, and can be set according to actual needs (such as percentage of distance, fixed value, etc.).

[0056] In an embodiment of the present invention, the sampling time point can be understood as the sampling time point when the reference curve is translated within the interval between the first distance and the second distance. The first distance can be the distance between the reference curve and the demarcation line dividing the first distance and the second distance. The second distance can be the distance between the target stratification curve and the demarcation line dividing the first distance and the second distance. The sampling time point can be determined according to the sampling reference time (sampling start time or the previous adjacent sampling time point) and the sampling time interval. The sampling time intervals at different translation positions within the first distance and the second distance can be the same or at least partially different, which is not limited herein. Exemplarily, the sampling time interval and the second distance can have a negative correlation relationship.

[0057] Based on the above solution, the determination of multiple second reference points of the stratification curve can include, but is not limited to, at least one of the following methods: selecting a preset number of target sampling points in the stratification curve through a target sampling interval and using the target sampling points as the second reference points; or, selecting a preset number of target sampling points in the stratification curve through a preset function and using the target sampling points as the second reference points, etc.

[0058] Among them, the target sampling interval can be understood as the interval between two consecutive sampling points during the acquisition of the second reference points. The target sampling interval can be uniform or non-uniform, which is not limited herein.

[0059] In an alternative embodiment, when determining the number of all sampling points of the stratification curve, the number of required second reference points can be determined first, and the target sampling points under the number of the stratification curve can be determined by using a random function, and the target sampling points are used as the second reference points.

[0060] Adopting this technical solution, by translating the reference curve and calculating the second position deviation amount between it and the stratification curve at multiple second reference points, and then selecting the translation curve with the smallest average position deviation amount as the reference curve, the automatic recognition of the boundaries of each layer of the retina is optimized, and the accuracy and reliability of the retina stratification structure analysis can be significantly improved.

[0061] S130. Determine the first position deviation amount between the reference curve and the stratification curve at the first reference point, determine the target statistical histogram according to the first position deviation amount, and determine the thickness feature data corresponding to the thickness of the retina tissue stratification according to the target statistical histogram.

[0062] Among them, the first reference point can be understood as all sampling points of the stratification curve in the tissue scan image of the retinal tissue. The first position deviation amount can be understood as the distance difference between the reference curve and other stratification curves at the first reference point, which is used to reflect the difference in the relative positions between the reference curve and other stratification curves. The target statistical histogram can be understood as a statistical histogram generated by statistically analyzing the data of multiple first position deviation amounts, which is used to display the distribution of the first position deviation amounts and helps to intuitively determine the variation law of the thickness between the various tissue layers of the retina. The thickness feature data can be understood as the evaluation result of the thickness of each layer of the retina determined according to the target statistical histogram, which can be used to evaluate the variation of the retinal stratification thickness.

[0063] Based on the above solution, optionally, determining the target statistical histogram according to the first position deviation amount includes: determining a plurality of position deviation intervals corresponding to the first position deviation amount according to a preset position deviation interval, and respectively determining the number of the first position deviation amounts within each position deviation interval; using the position deviation interval as the abscissa and the number as the ordinate to determine the target statistical histogram.

[0064] Among them, the position deviation interval can be understood as the interval size for classifying the first position deviation amount. The position deviation interval can be understood as dividing the first position deviation amount into a plurality of consecutive intervals according to the preset position deviation interval, and each interval represents the first position deviation amount within a certain range. The number of the first position deviation amounts can be understood as the number of the first position deviation amounts included in each position deviation interval, which can be used to reflect the frequency or density of the first position deviation amounts within a specific deviation range. The ordinate can represent the number of the first position deviation amounts within each position deviation interval, reflecting the frequency or density of the first position deviation amounts within this position deviation interval.

[0065] An optional implementation manner can be through Figure 4 the target statistical histogram shown in the figure to determine the number of the first position deviation amounts within different position deviation intervals.

[0066] Based on the above solution, optionally, after determining the thickness feature data corresponding to the retinal tissue stratification thickness according to the target statistical histogram, it further includes: determining a target data format corresponding to the thickness feature data, and displaying the thickness feature data in the target data format. Wherein, the target data format can be understood as the specific format for displaying the thickness feature data. Exemplarily, the target data format may include at least one of formats such as tables, graphs, and text reports. With this technical solution, by determining the target data format of the thickness feature data of the retinal tissue stratification thickness for display, the thickness feature data can be intuitively displayed, improving the interpretation and application of the thickness feature data.

[0067] In the technical solution of the embodiment of the present invention, by acquiring the tissue scan image of the retinal tissue and determining the stratification curves corresponding to multiple structural layers of the retinal tissue in the tissue scan image, each structural layer can be identified, providing sufficient data support for the subsequent processing of the tissue scan image; then, a reference curve is determined from multiple stratification curves, and the reference curve is moved along the arrangement direction of multiple structural layers to obtain a reference curve, since the reference curve is the reference curve located at the target position after movement, and the target position is the position where the coincidence degree between the reference curve and the stratification curve is the highest, improving the accuracy and automation level of retinal stratification analysis; finally, determining the first position deviation amount between the reference curve and the stratification curve at the first reference point, determining the target statistical histogram according to the first position deviation amount, and determining the thickness feature data corresponding to the retinal tissue stratification thickness according to the target statistical histogram, which can accurately quantify the thickness features of each layer of the retinal tissue, solves the problem in the related technology that it is difficult to accurately measure the retinal tissue stratification thickness relying on manual experience, significantly improves the accuracy and automation degree of retinal stratification thickness measurement, reduces human error, and improves the accuracy and detection efficiency of retinal tissue stratification thickness detection.

[0068] Embodiment 2

[0069] Figure 2The figure is a flowchart of a method for evaluating the layered thickness of retinal tissue provided in the second embodiment of the present invention. This embodiment further refines how to determine the thickness characteristic data corresponding to the layered thickness of the retinal tissue based on the target statistical histogram on the basis of the above embodiment. Optionally, determining the thickness characteristic data corresponding to the layered thickness of the retinal tissue according to the target statistical histogram includes: determining first thickness characteristic data corresponding to the layered thickness of the retinal tissue according to the target statistical histogram and a peak function, where the first thickness characteristic data includes at least one of the number of peak positions, peak positions, and thickness; and / or determining second thickness characteristic data corresponding to the layered thickness of the retinal tissue according to the target statistical histogram and a kurtosis function, where the second thickness characteristic data at least includes the degree of fluctuation. For the specific implementation, reference can be made to the description of this embodiment. Among them, the technical features that are the same as or similar to the foregoing embodiments will not be described in detail here.

[0070] As Figure 2 shown, the method may specifically include:

[0071] S210. Obtain a tissue scan image of the retinal tissue and determine a layered curve corresponding to multiple structural layers of the retinal tissue in the tissue scan image;

[0072] S220. Determine a reference curve from multiple layered curves, and move the reference curve along the arrangement direction of the multiple structural layers to obtain a reference curve; where the reference curve is the reference curve located at the target position after movement, and the target position is the position where the coincidence degree between the reference curve and the layered curve is the highest;

[0073] S230. Determine a first position deviation amount between the reference curve and the layered curve at a first reference point, determine a target statistical histogram according to the first position deviation amount, and determine first thickness characteristic data corresponding to the layered thickness of the retinal tissue according to the target statistical histogram and a peak function, where the first thickness characteristic data includes at least one of the number of peak positions, peak positions, and thickness.

[0074] Among them, the peak function can be understood as a function for analyzing the peak characteristics in the target statistical histogram, used to determine one or more local maxima in the target statistical histogram. The first thickness characteristic data can be understood as the retinal layer thickness characteristics determined according to the target statistical histogram and the peak function, including but not limited to at least one of the number of peak positions, peak positions, and thickness, etc. Figure 1 The first thickness characteristic data can be understood as the retinal layer thickness characteristics determined according to the target statistical histogram and the peak function, including but not limited to at least one of the number of peak positions, peak positions, and thickness, etc.

[0075] Based on the above solution, optionally, the determining the first thickness feature data corresponding to the retinal tissue stratification thickness according to the target statistical histogram and the peak function includes: for the ordinate of each of the position deviation intervals in the target statistical histogram, determining the peak function value corresponding to the ordinate through the peak function; for the peak function value of each of the position deviation intervals, obtaining the reference value corresponding to the peak function value; in the case where the peak function value is greater than the reference value, determining the position deviation interval corresponding to the peak function value as the peak position; and, determining the number of peak positions of the retinal tissue stratification thickness according to the total number of the peak positions in the target statistical histogram; and, determining the thickness corresponding to the peak position according to the peak position.

[0076] Among them, the peak function value can be understood as the value obtained by applying the peak function to the ordinate of the position deviation interval, which is used to measure the maximum value of the position deviation interval in a specific area. The reference value can be understood as the peak function values of a preset number of the position deviation intervals adjacent to the position deviation interval, which is used to determine whether the current position deviation interval constitutes a peak position. The preset number can be understood as a preset value. When determining whether a certain position deviation interval constitutes a peak position, it is necessary to consider the peak function values of multiple adjacent position deviation intervals as a reference. It can be understood that the larger the preset number, the more accurate the determined peak position. The peak position can be understood as when the peak function value of a certain position deviation interval is greater than its reference value, this position deviation interval can be considered as a peak position, representing the area with a higher data density in the target statistical histogram. The number of peak positions can be understood as the total sum of the quantities of all the position deviation intervals confirmed as peak positions in the target statistical histogram. The thickness can be understood as the retinal stratification thickness value determined according to the peak position, and the thickness can include at least one thickness feature such as the average thickness, the thinnest point, and the thickest point, etc.

[0077] Based on the above solution, specifically, the peak function is:

[0078]

[0079] Among them, P represents the peak function value corresponding to the ordinate, and the l n (·) represents the ordinate of the target statistical histogram corresponding to the nth stratification curve, L represents the preset position deviation interval, m represents the number of equal parts into which L is evenly divided, and h represents a positive integer less than m - 1.

[0080] Adopting this technical solution, by applying a peak function to analyze each position deviation interval in the target statistical histogram, determining the peak function value, comparing it with the reference value of the adjacent position deviation interval, identifying the peak position, and determining the number of peak positions and thickness based on the peak position, it is possible to accurately identify the key features of the retinal tissue stratification thickness, effectively screen out the significant thickness change points of the retinal tissue stratification, and contribute to the early diagnosis and evaluation of retinal diseases in medical images.

[0081] S240. Determine the second thickness feature data corresponding to the retinal tissue stratification thickness according to the target statistical histogram and the kurtosis function, where the second thickness feature data at least includes the degree of fluctuation.

[0082] Among them, the kurtosis function can be understood as a statistic used to evaluate the distribution form of the retinal tissue stratification thickness and can be used to measure the second thickness feature data of the retinal tissue stratification thickness. The second thickness feature data can be understood as the retinal stratification thickness feature determined according to the target statistical histogram and the kurtosis function, and the second thickness feature data may include but is not limited to the degree of fluctuation, etc.

[0083] On the basis of the above solution, optionally, the determining the second thickness feature data corresponding to the retinal tissue stratification thickness according to the target statistical histogram and the kurtosis function includes: determining the average value and standard deviation of the ordinate of the target statistical histogram, determining the kurtosis value according to the total number of the first reference points, the kurtosis function, the average value, and the standard deviation, and determining the degree of fluctuation of the retinal tissue stratification thickness according to the kurtosis value.

[0084] Among them, the kurtosis value can be understood as the specific value obtained after applying the kurtosis function and is used to quantify the degree of fluctuation of the statistical histogram data distribution. The degree of fluctuation can be understood as reflecting the degree of change of the retinal tissue stratification thickness at the first reference point. A higher degree of fluctuation may indicate significant structural variation or abnormality in the retinal tissue structure.

[0085] On the basis of the above solution, specifically, the kurtosis function is:

[0086]

[0087] Among them, l n (i) represents the ordinate of the i-th deviation interval of the target statistical histogram corresponding to the n-th stratification curve. represents the average value of the ordinate of the target statistical histogram, StDev represents the average value of the ordinate of the target statistical histogram, M represents the total number of the first reference points, i represents the i-th deviation interval in the target statistical histogram, and the value range of i is 0, 1,..., M - 1.

[0088] With this technical solution, by calculating the average value and standard deviation of the ordinate of the target statistical histogram, and determining the kurtosis value in combination with the total number of the first reference points and the kurtosis function, the undulation degree of the retinal tissue stratification thickness can be determined, which not only quantifies the severity of the retinal structure change, but also provides more refined structural information of the retinal tissue stratification.

[0089] It should be noted that in practical applications, S230 and S240 can be executed one by one, two by two, or all, depending on the thickness characteristic data to be displayed, and no specific limitation is made here.

[0090] The technical solution of the embodiment of the present invention uses the peak function to determine the peak function values corresponding to the ordinates of each position deviation interval, and compares them with the reference values of adjacent position deviation intervals to identify the significant peak positions, which can accurately determine the thickness and the number of peak positions of each layer of the retina, improve the measurement accuracy and reduce the manual error. Secondly, based on the kurtosis function combined with the average value and standard deviation of the target statistical histogram, the undulation degree of the retinal tissue stratification thickness is further evaluated, which not only captures the undulation degree of the thickness, but also provides quantitative information about the complexity of the thickness distribution, greatly improving the automation level, consistency and reliability of the retinal stratification thickness measurement.

[0091] Embodiment III

[0092] Figure 5 It is a schematic structural diagram of an evaluation device for the retinal tissue stratification thickness provided by Embodiment III of the present invention. As Figure 5 shown, the device includes: a stratification curve determination module 510, a reference curve determination module 520, and a thickness characteristic data determination module 530.

[0093] Among them, the stratification curve determination module 510 is used to obtain the tissue scan image of the retinal tissue and determine the stratification curve corresponding to multiple structural layers of the retinal tissue in the tissue scan image; the reference curve determination module 520 is used to determine a reference curve from multiple stratification curves, and move the reference curve along the arrangement direction of the multiple structural layers to obtain a reference curve; wherein, the reference curve is the reference curve located at the target position after movement, and the target position is the position where the coincidence degree between the reference curve and the stratification curve is the highest; the thickness characteristic data determination module 530 is used to determine the first position deviation amount between the reference curve and the stratification curve at the first reference point, determine the target statistical histogram according to the first position deviation amount, and determine the thickness characteristic data corresponding to the retinal tissue stratification thickness according to the target statistical histogram.

[0094] In the technical solution of the embodiment of the present invention, the tissue scanning image of the retinal tissue is obtained through the layer curve determination module 510, and the layer curves corresponding to multiple structural layers of the retinal tissue are determined in the tissue scanning image, so that each structural layer can be recognized, and sufficient data support is provided for the subsequent processing of the tissue scanning image; then, the reference curve is determined from multiple layer curves through the reference curve determination module 520, and the reference curve is moved along the arrangement direction of multiple structural layers to obtain the reference curve. Since the reference curve is the reference curve located at the target position after movement, and the target position is the position where the coincidence degree between the reference curve and the layer curve is the highest, the accuracy and automation level of retinal layer analysis are improved; finally, the thickness feature data determination module 530 determines the first position deviation amount between the reference curve and the layer curve at the first reference point, determines the target statistical histogram according to the first position deviation amount, and determines the thickness feature data corresponding to the retinal tissue layer thickness according to the target statistical histogram, which can accurately quantify the thickness features of each layer of the retinal tissue, solves the problem that it is difficult to accurately measure the retinal tissue layer thickness relying on manual experience in the related technology, significantly improves the accuracy and automation degree of retinal layer thickness measurement, reduces human errors, and improves the accuracy and detection efficiency of retinal tissue layer thickness detection.

[0095] On the basis of the above solution, optionally, the reference curve determination module includes: a translation sub-module, a second position deviation amount determination module, and a reference curve determination sub-module. Among them, the translation sub-module is used to translate the reference curve along the arrangement direction of multiple structural layers to obtain multiple translated curves; the second position deviation amount determination module is used to determine multiple second reference points of the layer curve, and for each translated curve, determine the second position deviation amount between the layer curve and the translated curve at multiple second reference points; the reference curve determination sub-module is used to determine the average position deviation amount of the second position deviation amounts at multiple second reference points, and determine the translated curve with the smallest average position deviation amount as the reference curve corresponding to the reference curve.

[0096] On the basis of the above solution, optionally, the thickness feature data determination module includes: a quantity determination sub-module, and a target statistical histogram determination sub-module. Among them, the quantity determination sub-module is used to determine multiple position deviation intervals corresponding to the first position deviation amount according to a preset position deviation interval, and respectively determine the quantity of the first position deviation amount in each position deviation interval; the target statistical histogram determination sub-module is used to use the position deviation interval as the abscissa and the quantity as the ordinate to determine the target statistical histogram.

[0097] Based on the above solution, optionally, the thickness feature data determination module includes: a first thickness feature data determination sub-module and a second thickness feature data determination sub-module. Among them, the first thickness feature data determination sub-module is used to determine first thickness feature data corresponding to the retinal tissue stratification thickness according to the target statistical histogram and the peak function, where the first thickness feature data includes at least one of the number of peak positions, peak position, and thickness; and / or, the second thickness feature data determination sub-module is used to determine second thickness feature data corresponding to the retinal tissue stratification thickness according to the target statistical histogram and the kurtosis function, where the second thickness feature data at least includes the degree of fluctuation.

[0098] Based on the above solution, optionally, the first thickness feature data determination sub-module includes: a peak function value determination unit, a reference value determination unit, a peak position determination unit, a peak number determination unit, and a thickness determination unit. Among them, the peak function value determination unit is used to determine the peak function value corresponding to the ordinate for each position deviation interval in the target statistical histogram through the peak function; the reference value determination unit is used to obtain the reference value corresponding to the peak function value for each position deviation interval, where the reference value includes the peak function values of a preset number of position deviation intervals adjacent to the position deviation interval; the peak position determination unit is used to determine the position deviation interval corresponding to the peak function value as the peak position when the peak function value is greater than the reference value; and, the peak number determination unit is used to determine the number of peak positions of the retinal tissue stratification thickness according to the total number of peak positions in the target statistical histogram; and, the thickness determination unit is used to determine the thickness corresponding to the peak position according to the peak position.

[0099] Based on the above solution, specifically, the peak function is:

[0100]

[0101] Among them, P represents the peak function value corresponding to the ordinate, and the l n (·) represents the ordinate of the target statistical histogram corresponding to the nth stratification curve, L represents the preset position deviation interval, m represents the number of equal parts into which L is divided, and h represents a positive integer less than m - 1.

[0102] Based on the above solution, optionally, the first thickness feature data determination sub-module includes: a fluctuation degree determination unit. The fluctuation degree determination unit is configured to determine the average value and the standard deviation of the ordinate of the target statistical histogram, determine the kurtosis value according to the total number of the first reference points, the kurtosis function, the average value and the standard deviation, and determine the fluctuation degree of the retinal tissue stratification thickness according to the kurtosis value.

[0103] Based on the above solution, specifically, the kurtosis function is:

[0104]

[0105] where l n (i) represents the ordinate of the i-th deviation interval of the target statistical histogram corresponding to the n-th stratification curve, represents the average value of the ordinate of the target statistical histogram, StDev represents the average value of the ordinate of the target statistical histogram, M represents the total number of the first reference points, i represents the i-th deviation interval in the target statistical histogram, and the value range of i is 0, 1,..., M-1.

[0106] Based on the above solution, optionally, the evaluation device for the retinal tissue stratification thickness further includes: a display module. The display module is configured to, after determining the thickness feature data corresponding to the retinal tissue stratification thickness according to the target statistical histogram, determine the target data format corresponding to the thickness feature data, and display the thickness feature data in the target data format.

[0107] The evaluation device for the retinal tissue stratification thickness provided by the embodiments of the present invention can execute the evaluation method for the retinal tissue stratification thickness provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0108] Embodiment 4

[0109] Figure 6 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0110] As shown Figure 6 in FIG. 1, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0111] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0112] The processor 11 can be various general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for evaluating the thickness of retinal tissue stratification.

[0113] Specifically, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium. The computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication unit 19, or installed from the storage unit 18, or installed from the ROM 12. When the computer program is executed by the processor 11, the above-mentioned functions defined in the method of the embodiment of the present invention are executed.

[0114] In some embodiments, a method for evaluating the layered thickness of retinal tissue can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for evaluating the layered thickness of retinal tissue described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute a method for evaluating the layered thickness of retinal tissue by any other suitable means (e.g., by means of firmware).

[0115] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer programs are executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0117] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0118] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0119] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0120] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is created by computer programs that run on respective computers and have a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0121] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0122] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for evaluating the layered thickness of retinal tissue, characterized in that, Including: Obtaining a tissue scan image of the retinal tissue and determining a layering curve corresponding to multiple structural layers of the retinal tissue in the tissue scan image; Determining a reference curve from multiple layering curves, and moving the reference curve along the arrangement direction of the multiple structural layers to obtain a reference curve; wherein, the reference curve is the reference curve located at the target position after movement, and the target position is the position where the coincidence degree between the reference curve and the layering curve is the highest; Determining a first position deviation amount between the reference curve and the layering curve at a first reference point, determining a target statistical histogram according to the first position deviation amount, and determining thickness characteristic data corresponding to the retinal tissue layering thickness according to the target statistical histogram.

2. The method for evaluating the retinal tissue stratification thickness according to claim 1, wherein The moving the reference curve along the arrangement direction of the multiple structural layers to obtain a reference curve includes: Translating the reference curve along the arrangement direction of the multiple structural layers to obtain multiple translated curves; Determining multiple second reference points of the layering curve, and for each translated curve, determining a second position deviation amount between the layering curve and the translated curve at the multiple second reference points; Determining an average position deviation amount of the second position deviation amounts at the multiple second reference points, and determining the translated curve with the smallest average position deviation amount as the reference curve corresponding to the reference curve.

3. The evaluation method of the retinal tissue stratification thickness according to claim 1, wherein The determining the target statistical histogram according to the first position deviation amount includes: Determining multiple position deviation intervals corresponding to the first position deviation amount according to a preset position deviation interval, and respectively determining the number of the first position deviation amounts in each position deviation interval; Taking the position deviation interval as the abscissa and the number as the ordinate to determine the target statistical histogram.

4. The evaluation method of the retinal tissue stratification thickness according to claim 1, wherein, The determining the thickness characteristic data corresponding to the retinal tissue layering thickness according to the target statistical histogram includes: Determining first thickness characteristic data corresponding to the retinal tissue layering thickness according to the target statistical histogram and a peak function, wherein the first thickness characteristic data includes at least one of the number of peak positions, peak position locations, and thickness; and / or, Determining second thickness characteristic data corresponding to the retinal tissue layering thickness according to the target statistical histogram and a kurtosis function, wherein the second thickness characteristic data at least includes the degree of fluctuation.

5. The evaluation method of the retinal tissue stratification thickness according to claim 4, wherein The determining the first thickness characteristic data corresponding to the retinal tissue layering thickness according to the target statistical histogram and the peak function includes: For the ordinate of each position deviation interval in the target statistical histogram, determining a peak function value corresponding to the ordinate through the peak function; For the peak function value of each position deviation interval, obtaining a reference value corresponding to the peak function value; wherein, the reference value includes peak function values of a preset number of position deviation intervals adjacent to the position deviation interval; In the case where the peak function value is greater than the reference value, determining the position deviation interval corresponding to the peak function value as the peak position location; and, Determine the number of peaks of the retinal tissue stratification thickness according to the total number of the peak positions in the target statistical histogram; and, Determine the corresponding thickness at the peak position according to the peak position.

6. The evaluation method of the retinal tissue stratification thickness according to claim 5, characterized in that The peak function is: where P represents the peak function value corresponding to the ordinate, and l n (·) represents the ordinate of the target statistical histogram corresponding to the nth stratified curve, L represents the preset position deviation interval, m represents the number of equal parts into which L is evenly divided, and h represents a positive integer less than m - 1.

7. The evaluation method for the retinal tissue stratification thickness according to claim 4, characterized in that The determination of the second thickness characteristic data corresponding to the retinal tissue stratification thickness according to the target statistical histogram and the kurtosis function includes: Determine the average value and the standard deviation of the ordinate of the target statistical histogram, determine the kurtosis value according to the total number of the first reference points, the kurtosis function, the average value and the standard deviation, and determine the undulation degree of the retinal tissue stratification thickness according to the kurtosis value.

8. The evaluation method of the retinal tissue stratification thickness according to claim 7, characterized in that The kurtosis function is: where l n (i) represents the ordinate of the i-th deviation interval of the target statistical histogram corresponding to the n-th hierarchical curve, and l n represents the average value of the ordinates of the target statistical histogram, StDev represents the average value of the ordinates of the target statistical histogram, M represents the total number of first reference points, i represents the i-th deviation interval in the target statistical histogram, and the value range of i is 0, 1,..., M - 1.

9. The evaluation method for the retinal tissue stratification thickness according to claim 1, wherein After determining the thickness characteristic data corresponding to the retinal tissue stratification thickness according to the target statistical histogram, it further includes: Determine the target data format corresponding to the thickness characteristic data, and display the thickness characteristic data in the target data format.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the processor to implement the evaluation method of the retinal tissue stratification thickness according to any one of claims 1-9 when executed.

Images