Method and device for detecting boundary of mutually infiltrated substances based on OCT (optical coherence tomography)

Abstract

The invention relates to the technical field of optical imaging edge detection, in particular to an OCT-based mutual infiltration substance boundary detection method and device, and the method comprises the steps: carrying out the OCT scanning imaging of a to-be-detected infiltration region, obtaining an OCT B-Scan image, decomposing the OCT B-Scan image into a plurality of A-line lines, recognizing the types of the A-line lines, mapping the A-line lines to the OCT B-Scan image, calculating the classification probability of each A-line, and carrying out the OCT scanning imaging of a to-be-detected infiltration region. And evaluating an edge identification and infiltration region, finally summarizing actual categories of each A-line, and mapping a result to an en-face image to determine a surface boundary region. Therefore, the problem that in the related technology, when an OCT imaging mode is used for recognizing the boundary of the mutual infiltration area in the complex substance, effective edge segmentation and quantitative analysis means are lacked, so that the accuracy of recognizing the boundary of the mutual infiltration area in the complex substance is not high is solved.

Description

Technical Field

[0001] This application relates to the technical field of optical imaging edge detection, and particularly to a method and device for detecting the boundary of mutually infiltrating substances based on OCT. Background Art

[0002] In the related art, as a high-resolution optical imaging method, OCT (Optical Coherence Tomograph) technology has developed rapidly in the field of medical imaging in recent years. OCT can provide high-depth-resolution images through non-invasive tomographic scanning of biological tissues, and is particularly suitable for application scenarios that require precise detection of microscopic structures.

[0003] However, in the related art, when the OCT imaging method is used to identify the boundary of the mutually infiltrating region in complex substances, there are lack of effective edge segmentation and quantitative analysis means, resulting in low accuracy in identifying the boundary of the mutually infiltrating region in complex substances, which urgently needs to be improved. Summary of the Invention

[0004] This application provides a method and device for detecting the boundary of mutually infiltrating substances based on OCT to solve the problem that in the related art, when the OCT imaging method is used to identify the boundary of the mutually infiltrating region in complex substances, there are lack of effective edge segmentation and quantitative analysis means, resulting in low accuracy in identifying the boundary of the mutually infiltrating region in complex substances.

[0005] The first aspect of this application provides a method for detecting the boundary of mutually infiltrating substances based on OCT, including the following steps: performing OCT scanning imaging on the edge region of the to-be-detected infiltration region to obtain the OCT B-Scan image of the to-be-detected infiltration region, and obtaining the basic information of the to-be-analyzed region; decomposing the OCT B-Scan image into multiple A-line lines, and identifying the actual category to which each A-line belongs; mapping the actual category to which each A-line belongs to the OCT B-Scan image to present the dividing line of different category regions on the OCT B-Scan image; calculating the classification probability of each A-line, and determining the quantitative evaluation result of edge recognition and infiltration region range based on the classification probability; based on the quantitative evaluation result, summarizing the actual category of each A-line in the to-be-analyzed region, and mapping it to the en-face image of the to-be-analyzed region, and combining the basic information to determine the surface boundary region.

[0006] Through the above technical solution, the embodiment of the present application can perform OCT scanning imaging on the to-be-detected infiltration area to obtain a high-resolution OCT B-Scan image, decompose it into multiple A-line lines, and then identify and classify the category to which each A-line belongs. By mapping the classification result back to the B-Scan image to form an obvious regional demarcation line and calculating the classification probability of each A-line, the accurate identification of the edge and the quantitative evaluation of the infiltration area are realized, which not only improves the accuracy and reliability of the edge detection of complex substances, but also can effectively identify the boundaries that are difficult to detect on the surface.

[0007] Optionally, in an embodiment of the present application, the calculating the classification probability of each A-line includes: obtaining the category label of each A-line; correcting the category label of each A-line to obtain the corrected A-line data; and training a classification model using the corrected A-line data to obtain the classification probability of each A-line.

[0008] Through the above technical solution, the embodiment of the present application can improve the accuracy of the classification model by correcting the category label of each A-line, thereby effectively improving the accuracy and reliability of edge detection. By training a classification model based on the corrected A-line data, the classification probability of each A-line can be calculated more accurately, and then the accurate identification of the mutually infiltrating areas in complex substances can be realized.

[0009] Optionally, in an embodiment of the present application, the obtaining the basic information of the area to be analyzed includes: collecting the depth information of the area to be analyzed; and / or collecting the structural information of the area to be analyzed.

[0010] Through the above technical solution, the embodiment of the present application can provide more comprehensive and accurate basic data for subsequent edge detection by obtaining the depth information and structural information of the area to be analyzed. This multi-dimensional information collection can improve the accuracy of edge detection and make the identification of the mutually infiltrating areas in complex substances more accurate.

[0011] Optionally, in an embodiment of the present application, the identifying the actual category to which each A-line belongs includes: performing clustering analysis on each A-line of the multiple A-line lines to obtain an analysis result; and determining the actual category to which each A-line belongs according to the analysis result.

[0012] Through the above technical solution, the embodiments of the present application can perform clustering analysis on multiple A-line lines to effectively identify the actual category to which each A-line belongs. This technical solution determines the category of each A-line based on the analysis results, thereby realizing the accurate boundary recognition of the mutually infiltrating regions and improving the accuracy and reliability of edge detection.

[0013] In a second aspect of the embodiments of the present application, a detection device for the boundary of mutually infiltrating substances based on OCT is provided, including: an acquisition module, configured to perform OCT scanning imaging on the edge region of the to-be-detected infiltration region to obtain an OCT B-Scan image of the to-be-detected infiltration region and obtain the basic information of the to-be-analyzed region; an identification module, configured to decompose the OCT B-Scan image into multiple A-line lines and identify the actual category to which each A-line belongs; a mapping module, configured to map the actual category to which each A-line belongs to the OCT B-Scan image to present the demarcation line of different category regions on the OCT B-Scan image; a calculation module, configured to calculate the classification probability of each A-line and determine the quantitative evaluation result of edge recognition and the infiltration region range based on the classification probability; a detection module, configured to summarize the actual category of each A-line in the to-be-analyzed region based on the quantitative evaluation result and map it onto the en-face image of the to-be-analyzed region, and combine with the basic information to determine the surface boundary region.

[0014] Through the above technical solution, the embodiments of the present application can perform OCT scanning imaging on the to-be-detected infiltration region, obtain a high-resolution OCT B-Scan image, decompose it into multiple A-line lines, and then identify and classify the category to which each A-line belongs. By mapping the classification result back to the B-Scan image to form an obvious regional demarcation line and calculating the classification probability of each A-line, the accurate recognition of the edge and the quantitative evaluation of the infiltration region are realized, which not only improves the accuracy and reliability of the edge detection of complex substances but also can effectively identify the boundaries that are difficult to detect on the surface.

[0015] Optionally, in an embodiment of the present application, the calculation module includes: an acquisition unit, configured to acquire the category label of each A-line; a correction unit, configured to correct the category label of each A-line to obtain the corrected A-line data; a training unit, configured to use the corrected A-line data to train a classification model to obtain the classification probability of each A-line.

[0016] Through the above technical solution, the embodiments of the present application can improve the accuracy of the classification model by correcting the category labels of each A-line, thereby effectively improving the accuracy and reliability of edge detection. By training a classification model based on the corrected A-line data, the classification probability of each A-line can be calculated more accurately, and then the accurate recognition of the mutually infiltrating regions in complex substances can be realized.

[0017] Optionally, in an embodiment of the present application, the obtaining module includes: a first acquisition unit for acquiring the depth information of the area to be analyzed; a second acquisition unit for acquiring the structure information of the area to be analyzed.

[0018] Through the above technical solution, the embodiments of the present application can provide more comprehensive and accurate basic data for subsequent edge detection by acquiring the depth information and structure information of the area to be analyzed. This multi-dimensional information acquisition can improve the accuracy of edge detection and make the recognition of the mutually infiltrating regions in complex substances more accurate.

[0019] Optionally, in an embodiment of the present application, the recognition module includes: a clustering analysis unit for performing clustering analysis on each of the multiple A-line lines to obtain an analysis result; a category discrimination unit for determining the actual category to which each A-line belongs according to the analysis result.

[0020] Through the above technical solution, the embodiments of the present application can effectively identify the actual category to which each A-line belongs by performing clustering analysis on multiple A-line lines. This technical solution determines the category of each A-line based on the analysis result, thereby realizing the accurate boundary recognition of the mutually infiltrating regions and improving the accuracy and reliability of edge detection.

[0021] An embodiment of the third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the method for detecting the boundary of mutually infiltrating substances based on OCT as described in the above embodiments.

[0022] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the program is executed by a processor, it implements the method for detecting the boundary of mutually infiltrating substances based on OCT as described above.

[0023] An embodiment of the fifth aspect of the present application provides a computer program, including a computer program, which when executed, is used to implement the method for detecting the boundary of mutually infiltrating substances based on OCT as described above.

[0024] Embodiments of the present application can perform OCT scanning imaging on the to-be-detected infiltration region, obtain high-resolution OCT B-Scan images, and decompose them into multiple A-line lines, thereby realizing the classification and recognition of each A-line. The classification results are mapped back to the B-Scan image to form obvious regional demarcation lines, and the classification probability of each A-line is calculated, so as to accurately identify the edges and quantify the infiltration region. In addition, by correcting the A-line category labels and training the classification model based on the corrected data, the accuracy of the classification model is further improved, the data processing process is optimized, and the recognition ability of the mutually infiltrating regions in complex substances is enhanced. This multi-dimensional information acquisition, combined with depth and structural information, provides comprehensive basic data for subsequent edge detection.

[0025] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Brief Description of the Drawings

[0026] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, where:

[0027] Figure 1 It is a flowchart of a method for detecting the boundary of mutually infiltrating substances based on OCT according to an embodiment of the present application;

[0028] Figure 2 It is a schematic diagram of a method for obtaining labels based on A-line clustering according to an embodiment of the present application;

[0029] Figure 3 It is a schematic diagram of a method for obtaining the probability distribution of two regions based on A-line according to an embodiment of the present application;

[0030] Figure 4 It is a schematic diagram of a method for obtaining the surface edge detection result of mutually infiltrating regions constructed by combining the en-face map reconstructed from the distribution probability and the en-face map reconstructed from the B-SCAN according to an embodiment of the present application;

[0031] Figure 5 It is a schematic diagram of the structure of a device for detecting the boundary of mutually infiltrating substances based on OCT according to an embodiment of the present application;

[0032] Figure 6 It is a schematic diagram of the structure example of an electronic device according to an embodiment of the present application. Detailed Embodiments

[0033] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as limiting the present application.

[0034] The detection method and device for the boundary of mutually infiltrating substances based on OCT according to the embodiments of the present application will be described below with reference to the accompanying drawings. In view of the problem in the related art mentioned in the above background art that in the OCT imaging method, when identifying the boundary of the mutually infiltrating region in complex substances, there is a lack of effective edge segmentation and quantitative analysis means, resulting in low accuracy in identifying the boundary of the mutually infiltrating region in complex substances, the present application provides a detection method for the boundary of mutually infiltrating substances based on OCT. In this method, an OCT B-Scan image with high resolution can be obtained by performing OCT scanning imaging on the region to be detected for infiltration, and it is decomposed into multiple A-line profiles, and then the category to which each A-line belongs is identified and classified. By mapping the classification results back to the B-Scan image, an obvious regional boundary line is formed, and the classification probability of each A-line is calculated, so as to achieve accurate identification of the edge and quantitative evaluation of the infiltration region, which not only improves the accuracy and reliability of edge detection of complex substances, but also can effectively identify the boundaries that are difficult to detect on the surface. Thus, the problem in the related art that in the OCT imaging method, when identifying the boundary of the mutually infiltrating region in complex substances, there is a lack of effective edge segmentation and quantitative analysis means, resulting in low accuracy in identifying the boundary of the mutually infiltrating region in complex substances is solved.

[0035] Specifically, Figure 1 FIG. is a schematic flow chart of a detection method for the boundary of mutually infiltrating substances based on OCT provided by the embodiments of the present application.

[0036] As Figure 1 shown, the detection method for the boundary of mutually infiltrating substances based on OCT includes the following steps:

[0037] In step S101, OCT scanning imaging is performed on the edge region of the region to be detected for infiltration to obtain an OCT B-Scan image of the tissue to be detected for lesions, and basic information of the region to be analyzed is obtained.

[0038] It can be understood that performing OCT imaging on the edge region of the region to be detected for infiltration to obtain an OCT B-Scan image of this region provides necessary basic data for subsequent edge detection, ensuring the accuracy and reliability of the detection.

[0039] Optionally, in an embodiment of the present application, basic information of the area to be analyzed is obtained, including: collecting depth information of the area to be analyzed; and / or collecting structural information of the area to be analyzed.

[0040] During the actual execution process, when performing OCT scanning imaging, the system will comprehensively scan the area to be analyzed. This process is not just simple image acquisition, but through high-resolution imaging technology, depth information and structural information of the area to be analyzed are obtained. Depth information refers to the longitudinal depth data of tissue layers obtained through OCT technology, which can reveal the hierarchical structure inside the tissue and help understand the relative positions and relationships between different tissues. Performing OCT scanning imaging on the area to be detected to generate OCT B-Scan image data, and obtaining the depth and structural information of the area to be analyzed, providing basic data for subsequent edge detection. Structural information refers to the tissue morphological features reflected in the OCT B-Scan image, including the boundaries, shapes of complex substances, and their mutual relationships with other surrounding substances. These information are crucial for identifying the boundaries of complex substances with unclear boundaries.

[0041] Specifically, through real-time OCT imaging in the embodiment of the present application, real-time optical tomography images of the mutually infiltrating areas that need to be finely identified can be obtained. In this process, not only OCT B-Scan image data can be generated, but also the boundaries of complex substances and their volume capacity information can be identified. The extraction of these information provides strong support for subsequent edge detection and ensures the accuracy of the detection results.

[0042] In the embodiment of the present application, OCT scanning imaging can be performed on the edge area of the detected infiltration area to obtain OCT B-Scan images and related depth and structural information, providing necessary basic data for subsequent edge detection. This process uses high-resolution imaging technology, which can not only capture the hierarchical structure of substances, but also reveal the boundaries and morphological features of substances, thereby effectively identifying the target recognition area of complex substances.

[0043] In step S102, the OCT B-Scan image is decomposed into multiple A-line lines, and the actual category to which each A-line belongs is identified.

[0044] It can be understood that an A-line represents signal information in the longitudinal depth direction and can reflect the hierarchical structure and characteristics of substances. Therefore, decomposing the OCT B-Scan image into multiple A-line lines can analyze the substance structure in the image more meticulously.

[0045] Optionally, in an embodiment of the present application, identifying the actual category to which each A-line belongs includes: performing clustering analysis on each A-line among multiple A-line lines to obtain an analysis result; and determining the actual category to which each A-line belongs according to the analysis result.

[0046] During the actual execution process, clustering analysis is performed on each A-line. This analysis process aims to group A-lines with similar characteristics into the same category through mathematical and statistical methods. The result of the clustering analysis can reveal the similarities and differences between different A-lines, thereby providing a basis for subsequent boundary recognition. The implementation of the clustering analysis is usually based on the digital features of the A-line, and these features may include but are not limited to information such as signal strength, shape, and texture. Through the comprehensive analysis of these features, it is possible to effectively distinguish the A-lines of different substances in complex substances.

[0047] Furthermore, according to the result of the clustering analysis, determine the actual category to which each A-line belongs. This process not only depends on the result of the clustering analysis, but also can combine the experience of relevant personnel to mark each A-line to ensure the accuracy and reliability of the classification, thereby initially distinguishing the boundary of the mutually infiltrating region and laying a foundation for subsequent edge detection and region recognition.

[0048] To further improve the accuracy of the classification, a label set of different substances can be pre-constructed based on the result of the clustering analysis using digital features, and the method for obtaining the labels is as Figure 2 shown. Such a label set can not only help us better understand the characteristics of the target detection substances, but also provide a solid foundation for the subsequent training of the classification model.

[0049] The embodiment of the present application can effectively identify the actual category to which each A-line belongs by decomposing the OCT B-Scan image into multiple A-lines and performing clustering analysis on each A-line. This process utilizes the longitudinal depth signal information of the A-line to carefully analyze the hierarchical structure and characteristics of biological tissues, thereby revealing the similarities and differences between different A-lines and providing an important basis for subsequent boundary recognition. The clustering analysis combines digital features such as signal strength, shape, and texture, and can accurately distinguish different substance categories in complex substances.

[0050] In step S103, map the actual category to which each A-line belongs to the OCT B-Scan image to present the boundary line of different category regions on the OCT B-Scan image.

[0051] During the actual execution process, the A-line category information obtained from the clustering analysis is mapped to the OCT B-Scan image, and the boundaries of different category regions are displayed on the image, thereby forming a clear category boundary effect on the B-Scan image.

[0052] Furthermore, the label set constructed in step S102 is mapped to the original A-lines. By combining the label information with the actual A-line data, it is possible to better identify and quantify the boundaries of the infiltration regions in subsequent analyses.

[0053] In the embodiment of the present application, by mapping the actual category information of each A-line to the OCT B-Scan image, the boundaries of different category regions can be clearly presented, thereby improving the visualization effect of the image and the accuracy of boundary recognition. This method not only optimizes the application of the clustering analysis results but also enhances the ability to identify and quantify the boundaries of the infiltration regions by combining the label information with the actual A-line data.

[0054] In step S104, the classification probability of each A-line is calculated, and based on the classification probability, the quantization evaluation results of edge recognition and the range of the infiltration region are determined.

[0055] Optionally, in an embodiment of the present application, calculating the classification probability of each A-line includes: obtaining the category label of each A-line; correcting the category label of each A-line to obtain the corrected A-line data; and training a classification model using the corrected A-line data to obtain the classification probability of each A-line.

[0056] Specifically, the category label of each A-line in the clustering analysis result is manually corrected, especially for the parts with large deviations, which are modified with emphasis. Through manual correction, more accurate corrected A-line data can be obtained.

[0057] Furthermore, using the corrected A-line data, it is used to train a classification model. Through training, the classification model can learn the feature differences between different categories and can obtain the classification probability of each A-line, as Figure 3 shown, and then based on these probability results, edge recognition and the quantization evaluation of the range of the infiltration region are realized.

[0058] Embodiments of the present application can significantly improve the detection accuracy by calculating the classification probability of each A-line and performing edge recognition and quantitative evaluation of the infiltration area range based on this. The method first obtains the class labels of each A-line and manually corrects the labels with large deviations to obtain more accurate corrected data. Then, using these corrected data to train a classification model, enabling it to effectively learn the feature differences between different classes, and finally output the classification probability of each A-line. This process ensures the reliability of edge recognition and the accurate evaluation of the infiltration area.

[0059] In step S105, based on the quantitative evaluation results, summarize the actual classes of each A-line in the area to be analyzed, and map them onto the en-face image of the area to be analyzed. Combine with the basic information to determine the surface boundary area.

[0060] In the actual execution process, by summarizing the classification results of each A-line in the entire area and mapping them to the en-face image, it is possible to combine depth information to identify the boundary areas where the surface is not obvious, further improving the accuracy and reliability of edge detection.

[0061] Furthermore, according to the en-face image reconstructed by combining the B-Scan and the calculated probability distribution en-face image, map the two images and display them in the same image to more intuitively display the detected edges. For example, Figure 4 As shown, taking the detection of the boundary of the diseased tissue as an example, by setting a threshold, those with a probability less than 1 can be classified as diseased tissue. In this way, the diseased area can be accurately resected, and more normal areas can be retained, which is beneficial to the patient's recovery and reduces functional damage.

[0062] Embodiments of the present application can effectively identify the boundary areas where the surface is not obvious by summarizing the classification results of each A-line in the area to be analyzed and mapping them onto the en-face image, and combining depth information, thereby significantly improving the accuracy and reliability of edge detection. In addition, by mapping and displaying the reconstructed B-Scan en-face image and the calculated probability distribution en-face image, the detected edges can be presented intuitively.

[0063] The detection method for the boundary of mutually infiltrating substances based on OCT according to the embodiments of the present application can perform OCT scanning imaging on the to-be-detected infiltration region, obtain a high-resolution OCT B-Scan image, and decompose it into multiple A-line lines, and then identify and classify the category to which each A-line belongs. By mapping the classification results back to the B-Scan image to form an obvious regional demarcation line and calculating the classification probability of each A-line, accurate identification of the edge and quantitative evaluation of the infiltration region are realized, which not only improves the accuracy and reliability of complex substance edge detection, but also can effectively identify the boundaries that are difficult to detect on the surface.

[0064] Next, a detection device for the boundary of mutually infiltrating substances based on OCT according to the embodiments of the present application will be described with reference to the accompanying drawings.

[0065] Figure 5 It is a block diagram of a detection device for the boundary of mutually infiltrating substances based on OCT according to the embodiments of the present application.

[0066] As Figure 5 shown, the detection device 10 for the boundary of mutually infiltrating substances based on OCT includes: an acquisition module 100, an identification module 200, a mapping module 300, a calculation module 400, and a detection module 500.

[0067] Specifically, the acquisition module 100 is configured to perform OCT scanning imaging on the edge region of the to-be-detected infiltration region to obtain an OCT B-Scan image of the to-be-detected lesion tissue and obtain the basic information of the region to be analyzed.

[0068] The identification module 200 is configured to decompose the OCT B-Scan image into multiple A-line lines and identify the actual category to which each A-line belongs.

[0069] The mapping module 300 is configured to map the actual category to which each A-line belongs to the OCT B-Scan image to present the demarcation line of different category regions on the OCT B-Scan image.

[0070] The calculation module 400 is configured to calculate the classification probability of each A-line and determine the quantitative evaluation result of edge recognition and the range of the infiltration region based on the classification probability.

[0071] The detection module 500 is configured to summarize the actual category of each A-line in the region to be analyzed based on the quantitative evaluation result, map it to the en-face image of the region to be analyzed, and combine the basic information to determine the surface boundary region.

[0072] Optionally, in an embodiment of the present application, the calculation module 400 includes: an acquisition unit, a correction unit, and a training unit.

[0073] Among them, an acquisition unit is configured to acquire the class label of each A-line.

[0074] A correction unit is configured to correct the class label of each A-line to obtain the corrected A-line data.

[0075] A training unit is configured to train a classification model by using the corrected A-line data to obtain the classification probability of each A-line.

[0076] Optionally, in an embodiment of the present application, the acquisition module 100 includes: a first acquisition unit and a second acquisition unit.

[0077] Among them, the first acquisition unit is configured to acquire the depth information of the area to be analyzed.

[0078] The second acquisition unit is configured to acquire the structure information of the area to be analyzed.

[0079] Optionally, in an embodiment of the present application, the recognition module 200 includes: a clustering analysis unit and a class discrimination unit.

[0080] Among them, the clustering analysis unit is configured to perform clustering analysis on each A-line of multiple A-line lines to obtain an analysis result.

[0081] The class discrimination unit is configured to determine the actual belonging class of each A-line according to the analysis result.

[0082] It should be noted that the foregoing explanation of the embodiment of the detection method for the boundary of mutually infiltrating substances based on OCT also applies to the detection device for the boundary of mutually infiltrating substances based on OCT in this embodiment, and details are not described herein again.

[0083] According to the detection device for the boundary of mutually infiltrating substances based on OCT proposed in the embodiment of the present application, it is possible to perform OCT scanning imaging on the area to be detected for infiltration, acquire a high-resolution OCT B-Scan image, decompose it into multiple A-line lines, and then identify and classify the belonging class of each A-line. By mapping the classification result back to the B-Scan image, an obvious area boundary line is formed, and the classification probability of each A-line is calculated, so as to realize accurate recognition of the edge and quantitative evaluation of the infiltration area. This not only improves the accuracy and reliability of complex substance edge detection, but also can effectively identify boundaries that are difficult to detect on the surface, has strong clinical application value, and helps with the accurate diagnosis and treatment of minimally invasive surgery.

[0084] Figure 6 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device may include:

[0085] A memory 601, a processor 602, and a computer program stored on the memory 601 and executable on the processor 602.

[0086] When the processor 602 executes the program, it implements the OCT-based detection method for the boundary of mutually infiltrating substances provided in the above embodiments.

[0087] Furthermore, the electronic device further includes:

[0088] A communication interface 603 for communication between the memory 601 and the processor 602.

[0089] The memory 601 is used to store a computer program executable on the processor 602.

[0090] The memory 601 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0091] If the memory 601, the processor 602, and the communication interface 603 are implemented independently, the communication interface 603, the memory 601, and the processor 602 can be interconnected through a bus and complete communication with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 6 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0092] Optionally, in a specific implementation, if the memory 601, the processor 602, and the communication interface 603 are integrated on a chip, the memory 601, the processor 602, and the communication interface 603 can complete communication with each other through an internal interface.

[0093] The processor 602 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0094] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-described method for detecting the boundary of mutually infiltrating substances based on OCT is implemented.

[0095] An embodiment of the present application further provides a computer program, including a computer program, which when executed, is used to implement the above-described method for detecting the boundary of mutually infiltrating substances based on OCT.

[0096] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0097] In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0098] Any process or method description in the flowchart or described in other ways herein can be understood to represent a module, segment, or part of code including one or N executable instructions for implementing a customized logical function or process, and the scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a manner that is not shown or discussed in order, including in a substantially simultaneous manner or in a reverse order according to the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0099] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in conjunction with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion (electronic device) having one or N wirings, 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). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0100] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or combinations thereof. In the above-described embodiments, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0101] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of the above-described embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0102] In addition, in each embodiment of the present application, each functional unit may be integrated in a processing module, may exist physically alone for each unit, or two or more units may be integrated in one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0103] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for detecting the boundary of mutually infiltrating materials based on OCT, characterized in that: The following steps are involved: Performing OCT scanning imaging on the infiltrated area to be detected to obtain an OCT B-Scan image of the infiltrated area to be detected and to obtain basic information of the area to be analyzed; Decomposing the OCT B-Scan image into a plurality of A-lines, and identifying the actual category to which each A-line actually belongs; Mapping the actual category to which each A-line belongs to the OCT B-Scan image to present a boundary line of different category areas on the OCT B-Scan image; Calculating the classification probability of each A-line, and determining the quantitative evaluation results of edge identification and infiltration area range based on the classification probability; Based on the quantitative evaluation result, the actual category of each A-line of the area to be analyzed is summarized and mapped to the en-face image of the area to be analyzed, and the surface boundary area is determined in combination with the basic information.

2. The method according to claim 1, characterized in that: The calculating the classification probability of each A-line includes: Get the category label of each A-line; Correcting the category label of each A-line to obtain corrected A-line data; The corrected A-line data is used to train a classification model to obtain the classification probability of each A-line.

3. The method according to claim 1, characterized in that The obtaining of basic information of the area to be analyzed includes: Collecting depth information of the area to be analyzed; And / or, collecting structural information of the area to be analyzed.

4. The method according to claim 1, characterized in that The identifying the actual category to which each A-line actually belongs includes: Performing cluster analysis on each A-line of the plurality of A-lines to obtain an analysis result; The actual category to which each A-line belongs is determined according to the analysis result.

5. An OCT-based detection device for mutually infiltrating material boundaries, characterized in that: include: An acquisition module is used to perform OCT scanning imaging on the infiltrated area to be detected, so as to obtain an OCTB-Scan image of the infiltrated area to be detected, and to obtain basic information of the area to be analyzed; A recognition module, used for decomposing the OCT B-Scan image into a plurality of A-lines and identifying the actual category to which each A-line actually belongs; A mapping module, used for mapping the actual category to which each A-line belongs to the OCT B-Scan image, so as to present the boundary lines of different category areas on the OCT B-Scan image; A calculation module, used to calculate the classification probability of each A-line, and determine the quantitative evaluation results of edge identification and infiltration area range based on the classification probability; A detection module is used to summarize the actual category of each A-line in the area to be analyzed based on the quantitative evaluation result, map it to the en-face image of the area to be analyzed, and determine the surface boundary area in combination with the basic information.

6. The device according to claim 5, characterized in that The computing module comprises: An acquisition unit is used to obtain the category label of each A-line; A correction unit, used for correcting the category label of each A-line to obtain corrected A-line data; A training unit is used to train a classification model using the corrected A-line data to obtain a classification probability of each A-line.

7. The device according to claim 5, characterized in that The acquisition module comprises: A first acquisition unit, used to acquire depth information of the area to be analyzed; The second acquisition unit is used to acquire the structural information of the area to be analyzed.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the OCT-based method for detecting boundaries of mutually infiltrating materials as described in any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the OCT-based method for detecting boundaries of mutually infiltrating materials as described in any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that The computer program is executed to implement the method for detecting the boundary of mutually infiltrating materials based on OCT according to any one of claims 1 to 4.

Images