A method for displaying layered results of OCT images

Abstract

The present invention provides a method for displaying layered results of an OCT image, wherein the OCT image is acquired by an optical coherence tomography scanner, and the method comprises: receiving a layered result viewing request for the OCT image sent by a user; and displaying a target layered result of the OCT image according to the layered result viewing request; wherein the target layered result comprises: a first layered result pre-defined by the user and / or a second layered result obtained by a neural network model. In this method, when the user needs to view the layered result of the OCT image, the pre-defined first layered result and / or the second layered result obtained by the neural network model can be automatically displayed to the user, without the need for manual adjustment by the user, which is more convenient to use and can improve diagnostic efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to a method for displaying layered results of OCT images. Background Art

[0002] Ophthalmic OCT (Optical Coherence Tomography) is a high-resolution ophthalmic imaging technology. OCT layering refers to separating and classifying the reflected signals in the OCT image according to their sources and characteristics to obtain a layered image of the tissue structure. Through layering, the boundaries and features of different tissue layers can be clearly visible, which helps doctors or researchers to conduct quantitative and qualitative analysis of the anatomical structure of the tissue. In related technologies, when doctors analyze the patient's condition, due to the complexity of the patient's condition, they often need to manually adjust the upper and lower boundaries of some of the above-mentioned layers to diagnose the condition, which is inconvenient to use and reduces the efficiency of diagnosis. Summary of the invention

[0003] The purpose of the present invention is to provide a method for displaying layered results of OCT images to improve diagnostic efficiency.

[0004] The present invention provides a method for displaying layered results of an OCT image, where the OCT image is acquired by an optical coherence tomography scanner. The method comprises: receiving a layered result viewing request for the OCT image sent by a user; and displaying a target layered result of the OCT image according to the layered result viewing request; wherein the target layered result comprises: a first layered result pre-defined by the user and / or a second layered result obtained by a neural network model.

[0005] Further, if the target hierarchical results include first hierarchical results and second hierarchical results, the display priority of the first hierarchical results is higher than the display priority of the second hierarchical results.

[0006] Furthermore, the first stratification result is determined by: obtaining multiple initial stratification results for OCT images that are pre-defined by the user; counting the usage frequency corresponding to each initial stratification result; and determining the initial stratification result with the highest usage frequency as the first stratification result.

[0007] Furthermore, the method for determining a customized first layer result includes: receiving a selection operation for a first layer line and a second layer line in an OCT image, and selecting the first layer line and the second layer line; receiving a modification instruction for a target layer line, and modifying the target layer line; wherein the target layer line includes the first layer line and / or the second layer line; and obtaining a first layer result based on the modified target layer line.

[0008] Furthermore, the method also includes: if the target layering line is the first layering line, in the process of modifying the first layering line, if there is a first intersection area between the first layering line and the adjacent third layering line, adjusting the first sub-layering line in the third layering line corresponding to the first intersection area so that the first sub-layering line fits the first layering line; if the target layering line is the second layering line, in the process of modifying the second layering line, if there is a second intersection area between the first layering line and the adjacent fourth layering line, adjusting the second sub-layering line in the fourth layering line corresponding to the second intersection area so that the second sub-layering line fits the second layering line.

[0009] Further, a modification instruction for the target layering line is received, and the step of modifying the target layering line includes: receiving a movement instruction for the target layering line, and modifying the target layering line according to the movement instruction.

[0010] Furthermore, a modification instruction for the target layering line is received, and the step of modifying the target layering line includes: receiving a displacement parameter adjustment instruction for the target layering line, determining a displacement adjustment amount; and modifying the target layering line according to the displacement adjustment amount.

[0011] Furthermore, the OCT image includes lesion information; the second layered result is obtained by inputting the OCT image into the neural network model, and outputting the second layered result matching the lesion information through the neural network model.

[0012] Furthermore, the lesion information includes at least one of the following: lesion location, lesion shape and lesion size.

[0013] Furthermore, the OCT image is a B-scan image or a three-dimensional image corresponding to the volume data.

[0014] The present invention provides a method for displaying layered results of an OCT image, wherein the OCT image is collected by an optical coherence tomography scanner, and the method comprises: receiving a layered result viewing request for the OCT image sent by a user; and displaying a target layered result of the OCT image according to the layered result viewing request; wherein the target layered result comprises: a first layered result pre-defined by the user and / or a second layered result obtained by a neural network model. In this method, when the user needs to view the layered result of the OCT image, the pre-defined first layered result and / or the second layered result obtained by the neural network model can be automatically displayed to the user, without the need for manual adjustment by the user, which is more convenient to use and can improve diagnostic efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A schematic diagram of an OCT image provided by an embodiment of the present invention;

[0017] Figure 2 A flowchart of a method for displaying layered results of an OCT image provided by an embodiment of the present invention;

[0018] Figure 3 A schematic diagram of a parameter setting interface provided by an embodiment of the present invention;

[0019] FIG4( a ) is a schematic diagram of a target layering line before being modified provided by an embodiment of the present invention;

[0020] FIG4( b ) is a schematic diagram of a target layering line after being modified according to an embodiment of the present invention;

[0021] Figure 5 A schematic diagram of the effect after a bonding process provided by an embodiment of the present invention;

[0022] Figure 6 A schematic diagram of a system architecture provided for an embodiment of the present invention;

[0023] Figure 7 A schematic diagram of a retinal image provided by an embodiment of the present invention;

[0024] Figure 8 A schematic diagram of a parameter setting interface provided by an embodiment of the present invention;

[0025] Fig. 9 A schematic diagram of a target stratification result provided by an embodiment of the present invention;

[0026] Fig.10 A schematic diagram of the structure of a device for displaying layered results of an OCT image provided by an embodiment of the present invention;

[0027] Fig.11 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] By layering OCT images, the boundaries and features of different tissue layers can be clearly seen, which helps doctors or researchers to conduct quantitative and qualitative analysis of the anatomical structure of tissues, such as Figure 1 A schematic diagram of an OCT image is shown. Figure 1 ① is the conventional stratification, which is predefined by the system. The conventional stratification listed in this embodiment from top to bottom is the retinal layer of the posterior segment of the eye, the inner retinal layer, the superficial vascular complex, the deep vascular complex, the retinal avascular layer, the choroidal capillary layer, the choroid layer, the vitreous layer, the radial capillary network, the superficial vascular network, the middle capillary network, the deep capillary network, the outer retinal layer and the pigment epithelial detachment layer. The above conventional stratification is only for illustration. Due to different system configurations, the conventional stratification may be different. ② in the figure is a B-scan image, ③ in the figure is an OCT vascular imaging projection (OCT Angio Projection) generated according to the stratification selected in ①, and ④ in the figure is an OCT structural imaging projection (OCT Structural Projection) generated according to the stratification selected in ①. In the related art, when a doctor analyzes a patient's condition, due to the complexity of the patient's condition, the conventional stratification is directly displayed to the user. The stratification results obtained according to the conventional stratification may not meet the doctor's needs. The doctor is often required to manually adjust the upper and lower boundaries of some of the above stratification results to diagnose the condition, which is inconvenient to use and reduces the diagnostic efficiency. Based on this, an embodiment of the present invention provides a method for displaying layered results of an OCT image. This technology can be applied to applications that require layering of OCT images.

[0030] To facilitate understanding of this embodiment, firstly, a method for displaying layered results of an OCT image disclosed in an embodiment of the present invention is introduced. The OCT image is collected by an optical coherence tomography scanner, which is a device for diagnostic imaging based on optical principles and can provide images of retinal cross-sections for objective quantitative measurement and qualitative clinical analysis when detecting glaucoma and retinopathy. The OCT image can be a B-scan image, a structural projection image, a blood flow image corresponding to the B-scan or a blood flow projection image corresponding to the structural projection image, etc.; the method can be applied to a server, such as Figure 2 As shown, the method comprises the following steps:

[0031] Step S202: receiving a layered result viewing request for an OCT image sent by a user.

[0032] The above-mentioned users may specifically be doctors, researchers and other persons who need to view the stratified results. For the sake of convenience, taking the user being a doctor as an example, in actual implementation, the doctor usually obtains the patient's OCT image in advance. When it is necessary to analyze the patient's related symptoms, a stratified result viewing request for the OCT image can be sent to the server. For example, relevant controls such as "View stratified results" can be clicked to send the stratified result viewing request.

[0033] Step S204, displaying the target layering result of the OCT image according to the layering result viewing request; wherein the target layering result includes: a first layering result pre-defined by the user and / or a second layering result obtained by a neural network model.

[0034] The first stratification result is usually a stratification result for the OCT image pre-adjusted by the user according to habit or experience; the second stratification result can be a stratification result obtained by analyzing the OCT image through a pre-trained neural network model; the neural network model can be implemented by a residual network or a VGG network, etc., which can be selected according to actual needs and is not limited here; in actual implementation, the server usually pre-stores the first stratification result and / or the second stratification result corresponding to the OCT image. When the server receives the stratification result viewing request sent by the user, the corresponding target stratification result can be extracted from the stored data; for example, if the server If only the first layer result is stored, the first layer result can be directly extracted and displayed; if only the second layer result is stored in the server, the second layer result can be directly extracted and displayed; if the first layer result and the second layer result are stored in the server at the same time, only the first layer result can be extracted and displayed, or only the second layer result can be extracted and displayed, or the first layer result and the second layer result can be extracted and displayed at the same time. The specific settings can be made according to actual needs, and the display method is more flexible; when displaying specifically, the extracted target layer result can also be sent to the terminal device corresponding to the user, and the target layer result can be displayed to the user through the terminal device.

[0035] The above-mentioned method for displaying the layered results of OCT images receives a layered result viewing request for the OCT image sent by the user; and displays the target layered result of the OCT image according to the layered result viewing request; wherein the target layered result includes: the first layered result pre-defined by the user and / or the second layered result obtained by the neural network model. In this method, when the user needs to view the layered results of the OCT image, the pre-defined first layered result and / or the second layered result obtained by the neural network model can be automatically displayed to the user, without the need for manual adjustment by the user, which is more convenient to use and can improve diagnostic efficiency.

[0036] The embodiment of the present invention further provides another method for displaying layered results of OCT images. The method is implemented on the basis of the method of the above embodiment, and the method comprises the following steps:

[0037] Step 1: receiving a layered result viewing request for an OCT image sent by a user.

[0038] The OCT image may be a B-scan image or a three-dimensional image corresponding to the volume data. Preferably, the OCT image contains the patient's retinal information. The volume data may be three-dimensional OCT volume data containing the retinal area obtained by line-by-line scanning based on the OCT technology.

[0039] Step 2: Display the target layering result of the OCT image according to the layering result viewing request; wherein the target layering result includes: the first layering result pre-defined by the user and / or the second layering result obtained by the neural network model.

[0040] If the target hierarchical results include the first hierarchical results and the second hierarchical results, the display priority of the first hierarchical results is higher than the display priority of the second hierarchical results. In actual implementation, when the target hierarchical results include both the first hierarchical results and the second hierarchical results, a corresponding display priority can be set for each hierarchical result. Considering that the first hierarchical result is a user-defined hierarchical result, which is usually more in line with the user's habits or analysis requirements, the display priority of the first hierarchical result can be set higher than the display priority of the second hierarchical result, that is, the first hierarchical result is displayed to the user first.

[0041] The first stratification result is determined by the following steps 21 to 23:

[0042] Step 21, obtaining a plurality of initial layering results for the OCT image that are pre-defined by the user.

[0043] Step 22, counting the usage frequency corresponding to each initial stratification result.

[0044] Step 23: determine the initial stratification result with the highest usage frequency as the first stratification result.

[0045] In actual implementation, the user may pre-customize a variety of different initial stratification results for the same OCT image. In different initial stratification results, the positions of the upper boundary line and / or lower boundary line of the same structural layer may be different. The frequency of use of each initial stratification result by the user can be counted. Generally, the higher the frequency of use, the more times the user uses the corresponding initial stratification result, and it can be considered that the corresponding initial stratification result more meets the user's actual analysis needs. Therefore, the initial stratification result with the highest frequency of use can be selected from multiple initial stratification results as the first stratification result.

[0046] The method for determining the customized first layer result can also be implemented by following steps A to C:

[0047] Step A: receiving a selection operation for a first slice line and a second slice line in an OCT image, and selecting the first slice line and the second slice line.

[0048] The above-mentioned first layering line can be a layering line corresponding to the benchmark upper boundary in the OCT image; the second layering line can be a layering line corresponding to the benchmark lower boundary in the OCT image; the benchmark upper boundary can be the upper boundary line or lower boundary line corresponding to the first specified structure in the OCT image, and the benchmark lower boundary can be the upper boundary line or lower boundary line corresponding to the second specified structure in the OCT image; the first specified structure and the second specified structure can be the same structure or different structures. If they are different structures, in the B-scan cross-sectional view of the OCT image, the first specified structure is usually located above the second specified structure; if they are the same structure, the benchmark upper boundary is the upper boundary line of the structure, and the benchmark lower boundary is the lower boundary line of the structure; in actual implementation, when the user needs to customize the first layering result, the first layering line and the second layering line in the OCT image can be selected first.

[0049] Step B, receiving a modification instruction for a target layer line, and modifying the target layer line; wherein the target layer line includes a first layer line and / or a second layer line.

[0050] After the user selects the first layer line and the second layer line, the user can choose to modify only the first layer line, or only the second layer line, or both the first layer line and the second layer line according to actual needs.

[0051] This step B can be implemented by following the steps B1:

[0052] Step B1, receiving a movement instruction for a target layer line, and modifying the target layer line according to the movement instruction.

[0053] In actual implementation, the user can directly move the target layer line through the terminal device to modify the position of the target layer line, which is more convenient to operate; for example, if the display screen of the terminal device is a touch screen, the user can press and hold the target layer line with a finger to move it; if the user operates the target layer line through a mouse, keyboard, etc., the target layer line can be selected with the mouse, and then the mouse can be dragged to move the target layer line; during the movement process, the movement effect can be displayed to the user in real time, so that the user can adjust the moving position in time, and the real-time interactivity is better. It should be noted that when the user makes custom adjustments, the position and / or shape of the target layer line can be adjusted, that is, only the position of the target layer line can be adjusted, and the shape remains unchanged; or the position of the target layer line can be adjusted without adjusting the shape; of course, the position and shape of the target layer line can also be adjusted at the same time, which can be selected according to actual needs and is not limited here.

[0054] This step B can also be implemented by following steps B2 and B3:

[0055] Step B2, receiving a displacement parameter adjustment instruction for the target layer line, and determining a displacement adjustment amount.

[0056] Step B3, modifying the target layering line according to the displacement adjustment amount.

[0057] In actual implementation, users can also modify the target layer line by inputting the displacement adjustment amount, see Figure 3 A schematic diagram of a parameter setting interface is shown, where ① represents the custom layer name, and ② can select the upper and lower base boundaries of the custom layer, for example, Figure 2 The upper reference boundary Upper is the boundary between the structure NFL (nerve fiber layer) and the structure GCL (ganglion cell layer); the lower reference boundary Lower is 1 / 3GCC (ganglion cell complex); ③ is to adjust the upper and lower displacements according to the upper and lower reference boundaries selected in ②. Users can define new layer names, upper reference boundaries, lower reference boundaries and corresponding displacement adjustments according to their needs. The position of the target layer line can be adjusted according to the displacement adjustment input by the user.

[0058] Step C, obtaining a first stratification result based on the modified target stratification line.

[0059] After the target hierarchical line is modified, the first hierarchical result can be obtained. The server can automatically add the first hierarchical result added by the user to the hierarchical information database according to the user's ID (Identity document) and automatically apply it to the patient data. It can be understood that the hierarchical information database can classify the stored data using a mechanism of classifying according to the user's ID.

[0060] Step D: if the target layering line is the first layering line, in the process of modifying the first layering line, if there is a first intersection area between the first layering line and the adjacent third layering line, adjust the first sub-layering line in the third layering line corresponding to the first intersection area to make the first sub-layering line fit with the first layering line.

[0061] The third layering line may be a boundary line of an upper layer adjacent to the first layering line, or may be a boundary line of a lower layer adjacent to the first layering line. The number of third layering lines may be one or more. The third layering line may be the same layering line as the second layering line, or may be a layering line different from the second layering line. For example, if the first layering line and the second layering line correspond to the upper and lower boundaries of the same structure respectively, then if the user controls the first layering line to move upward and crosses the adjacent boundary line of the upper layer, then the adjacent boundary line of the upper layer corresponds to the third layering line. If the user controls the first layering line to move downward and crosses the adjacent boundary line of the lower layer, then the adjacent boundary line of the lower layer corresponds to the third layering line, and at this time the third layering line is also the second layering line. In actual implementation, when modifying the first layering line, In the process of slicing a layer, the first layer line may be infinitely close to the adjacent third layer line, or even partially overlap or exceed the third layer line, wherein the area where the first layer line and the third layer line intersect corresponds to the above-mentioned first intersection area. However, in the actual stratum basal surface structure, there is no intersection between layers, and the arrangement order of the layer lines at various locations is consistent. When the above situation occurs, the first sub-layer line in the third layer line corresponding to the first intersection area will automatically fit with the first layer line, that is, the first layer line and the third layer line are not allowed to intersect. It should be noted that the fitting here can be the coincidence of the first sub-layer line and the first layer line, or the first sub-layer line and the first layer line can be separated by a preset distance, and the preset distance is usually a smaller distance value.

[0062] Step E: if the target layering line is the second layering line, in the process of modifying the second layering line, if there is a second intersection area between the second layering line and the adjacent fourth layering line, adjust the second sub-layering line in the fourth layering line corresponding to the second intersection area so that the second sub-layering line fits the second layering line.

[0063] The fourth layering line may be the upper layer boundary line adjacent to the second layering line, or may be the lower layer boundary line adjacent to the second layering line. The number of fourth layering lines may be one or more. The fourth layering line may be the same layering line as the first layering line, or may be a layering line different from the first layering line. For example, if the first layering line and the second layering line correspond to the upper boundary and the lower boundary of the same structure respectively, then if the user controls the second layering line to move downward and crosses the adjacent lower layer boundary line, then the adjacent lower layer boundary line corresponds to the fourth layering line. If the user controls the second layering line to move upward and crosses the adjacent upper layer boundary line, then the adjacent upper layer boundary line corresponds to the fourth layering line, and at this time the fourth layering line is also the first layering line. In actual implementation, when modifying the first layering line, In the process of dividing the two layers, it is possible that the second layer line is infinitely close to the adjacent fourth layer line, or even that the second layer line partially overlaps with or exceeds the fourth layer line, wherein the area where the second layer line and the fourth layer line intersect corresponds to the above-mentioned second intersection area. However, in the actual basal surface structure of the eye, there is no intersection between layers, and the arrangement order of the layer lines at various locations is consistent. When the above situation occurs, the second sub-layer line corresponding to the second intersection area in the fourth layer line will automatically fit with the second layer line, that is, the second layer line and the fourth layer line are not allowed to intersect. It should be noted that the fitting here can be the coincidence of the second sub-layer line and the second layer line, or the second sub-layer line and the second layer line can be separated by a preset distance, which is usually a smaller distance value.

[0064] Refer to FIG4(a), which is a schematic diagram of a target layering line before being modified, and FIG4(b), which is a schematic diagram of a target layering line after being modified. It can be seen from FIG4(a) that before the target layering line is modified, there is no intersection between the layers. It can be seen from FIG4(b) that after the shape of the target layering line is adjusted, it will intersect with the adjacent layering line of the next layer. At this time, in order to avoid intersection, the part of the adjacent layering line of the next layer that intersects with the target layering line will be automatically fitted to fit the target layering line to avoid intersection.

[0065] like Figure 5 As shown in the schematic diagram of the effect after the fitting process, it can be seen that no matter how the shape of the target layering line changes, the adjacent layering lines that intersect with it will automatically fit the target layering line without any intersection.

[0066] The OCT image includes lesion information; the lesion information includes at least one of the following: lesion location, lesion shape and lesion size. A lesion refers to a part of the body where a disease occurs. A localized diseased tissue with pathogenic microorganisms is called a lesion. The lesion location, lesion shape or lesion size of different lesions are usually different. The lesion information can be determined based on B-scan images, OCT structural imaging projections or positioning maps. The above second layering result can be obtained by following the steps F:

[0067] Step F, inputting the OCT image into the neural network model, and outputting the second layer result matching the lesion information through the neural network model.

[0068] The OCT image containing lesion information can be input into a pre-trained neural network model, and the corresponding second-layer result can be directly output through the neural network model; for example, some lesions have edema, which will cause the relevant structural stratification to be different from the conventional one. The neural network model can be used to analyze the lesion characteristics of the collected data and the verification information of the service user, and output the corresponding second-layer result.

[0069] In actual implementation, during the training of the neural network model, the user-defined first-layer results can be used as training data to train the neural network model, which can improve the task processing performance of the neural network model. After the OCT image is input into the neural network model trained in this way, the output second-layer results can be more in line with the actual needs of the user.

[0070] In addition, the best stratification scheme can be recommended to users through big data search based on the lesion characteristics of the collected data and the verification information of the user who called the service. When there are similar lesion characteristics, the stratification results defined by other users may be matched.

[0071] For ease of understanding, the following is provided Figure 6 A schematic diagram of a system architecture is shown, which mainly includes the following modules: log collection, full-text retrieval, data processing, data integration, database engine, deep mining computing engine, data management, basic framework, local server and private cloud server, among which data management, database engine and deep mining computing engine are three modules improved in this scheme. The data management module can summarize and manage the received user-defined hierarchical information, and perform preliminary screening through the database engine. For example, if the hierarchical position information of the customized layer is the same but the name is different, there will be a screening and filtering process, and only one storage is retained; after the OCT image containing lesion information is collected, it can be analyzed and processed through the deep mining computing engine (corresponding to the above-mentioned neural network model) to obtain the final second layer result, Figure 6The functions of other modules in the can refer to the relevant technology, which will not be repeated here; according to the user's verification information and the above-mentioned user-defined hierarchical information, Figure 6 The data processing and data integration modules in the data processing and data integration module form a set of regular hierarchical data information and store it in the local server or private cloud server, that is, the first hierarchical results and the second hierarchical results are stored in the database corresponding to the local server or the private cloud server. For example, taking the hospital as an example, the local server can be understood as the server corresponding to the hospital, and the private cloud server can be the server corresponding to different hospitals.

[0072] For easier understanding, see Figure 7 A schematic diagram of a retinal image is shown, and Figure 8 A schematic diagram of a parameter setting interface is shown in FIG. Figure 7 In the process, the user observes the vascular changes in the patient's inner nuclear layer. The automatically generated layers cannot observe this change. Figure 8 , add a custom layer named 111, you can enter the displacement adjustment amount to adjust the target layer line to move up or down to the corresponding structural layer; or you can drag Figure 7 The data is then switched to the 111 layer, such as Fig. 9 The schematic diagram of a target stratification result shown in the figure can clearly show the vascular changes in the inner nuclear layer. Afterwards, as long as there is similar data, the stratification result can be automatically displayed to the user to assist the user in diagnosis.

[0073] The above-mentioned method for displaying the layered results of OCT images can automatically display the pre-customized first layered results and / or the second layered results obtained by the neural network model to the user when the user needs to view the layered results of the OCT image. There is no need for manual adjustment by the user, which is more convenient to use and can improve diagnostic efficiency.

[0074] The embodiment of the present invention provides a device for displaying layered results of an OCT image, wherein the OCT image is acquired by an optical coherence tomography scanner, such as Fig.10 As shown, the device includes: a receiving module 110, used to receive a layered result viewing request for an OCT image sent by a user; a display module 111, used to display a target layered result of the OCT image according to the layered result viewing request; wherein the target layered result includes: a first layered result pre-customized by the user and / or a second layered result obtained through a neural network model.

[0075] The above-mentioned OCT image stratification result display device can automatically display the pre-customized first stratification result and / or the second stratification result obtained by the neural network model to the user when the user needs to view the stratification result of the OCT image. The user does not need to make manual adjustments, which is more convenient to use and can improve diagnostic efficiency.

[0076] Further, if the target hierarchical results include first hierarchical results and second hierarchical results, the display priority of the first hierarchical results is higher than the display priority of the second hierarchical results.

[0077] Furthermore, the device also includes a first stratification result determination module, and the first stratification result is determined by the first stratification result determination module, and the first stratification result determination module is used to: obtain multiple initial stratification results for the OCT image that are pre-customized by the user; count the usage frequency corresponding to each initial stratification result; and determine the initial stratification result with the highest usage frequency as the first stratification result.

[0078] Furthermore, the device also includes a first layering result acquisition module, which is used to: receive a selection operation for a first layer line and a second layer line in the OCT image, and select the first layer line and the second layer line; receive a modification instruction for a target layer line, and modify the target layer line; wherein the target layer line includes the first layer line and / or the second layer line; and obtain a first layering result based on the modified target layer line.

[0079] Furthermore, the first stratification result acquisition module is also used for: if the target stratification line is the first stratification line, in the process of modifying the first stratification line, if there is a first intersection area between the first stratification line and the adjacent third stratification line, adjust the first sub-stratification line in the third stratification line corresponding to the first intersection area so that the first sub-stratification line fits the first stratification line; if the target stratification line is the second stratification line, in the process of modifying the second stratification line, if there is a second intersection area between the second stratification line and the adjacent fourth stratification line, adjust the second sub-stratification line in the fourth stratification line corresponding to the second intersection area so that the second sub-stratification line fits the second stratification line.

[0080] Furthermore, the first layering result acquisition module is also used to: receive a movement instruction for a target layering line, and modify the target layering line according to the movement instruction.

[0081] Furthermore, the first stratification result acquisition module is also used to receive a modification instruction for the target stratification line, and the step of modifying the target stratification line includes: receiving a displacement parameter adjustment instruction for the target stratification line, determining a displacement adjustment amount; and modifying the target stratification line according to the displacement adjustment amount.

[0082] Furthermore, the device also includes a second layered result acquisition module, and the OCT image includes lesion information; the second layered result is obtained through the second layered result acquisition module, and the second layered result acquisition module is used to: input the OCT image into the neural network model, and output the second layered result matching the lesion information through the neural network model.

[0083] Furthermore, the lesion information includes at least one of the following: lesion location, lesion shape and lesion size.

[0084] The implementation principle and technical effects of the OCT image layered result display device provided in the embodiment of the present invention are the same as those of the aforementioned OCT image layered result display method embodiment. For the sake of brief description, for matters not mentioned in the embodiment of the OCT image layered result display device, reference may be made to the corresponding contents in the aforementioned OCT image layered result display method embodiment.

[0085] The embodiment of the present invention further provides an electronic device, see Fig.11 As shown, the electronic device includes a processor 130 and a memory 131 , wherein the memory 131 stores machine executable instructions that can be executed by the processor 130 , and the processor 130 executes the machine executable instructions to implement the above-mentioned layered result display method of the OCT image.

[0086] Further, Fig.11 The electronic device shown further includes a bus 132 and a communication interface 133 , and the processor 130 , the communication interface 133 and the memory 131 are connected via the bus 132 .

[0087] The memory 131 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 133 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 132 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.11 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0088] The processor 130 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 130. The above processor 130 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 131, and the processor 130 reads the information in the memory 131 and completes the steps of the method of the above embodiment in combination with its hardware.

[0089] An embodiment of the present invention also provides a machine-readable storage medium, which stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to implement the above-mentioned OCT image layered result display method. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0090] The computer program product of the layered result display method of OCT images provided in the embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the previous method embodiment. The specific implementation can be found in the method embodiment and will not be repeated here.

[0091] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for displaying layered results of an OCT image, wherein the OCT image is acquired by an optical coherence tomography scanner, characterized in that: The method comprises: receiving a layered result viewing request for the OCT image sent by a user; According to the layered result viewing request, display the target layered result of the OCT image; wherein the target layered result includes: the first layered result pre-defined by the user and / or the second layered result obtained by the neural network model; The method for determining the customized first-layer result includes: receiving a selection operation for a first layer line and a second layer line in the OCT image, and selecting the first layer line and the second layer line; receiving a modification instruction for a target layering line, and modifying the target layering line; wherein the target layering line includes a first layering line and / or the second layering line; Based on the modified target stratification line, obtaining the first stratification result; The method further comprises: If the target layering line is a first layering line, in the process of modifying the first layering line, if there is a first intersection region between the first layering line and an adjacent third layering line, a first sub-layering line corresponding to the first intersection region in the third layering line is adjusted so that the first sub-layering line is automatically aligned with the first layering line; wherein the aligned first sub-layering line is overlapped with the first layering line or separated by a preset distance; If the target layering line is the second layering line, in the process of modifying the second layering line, if there is a second intersection area between the second layering line and the adjacent fourth layering line, adjust the second sub-layering line in the fourth layering line corresponding to the second intersection area so that the second sub-layering line is automatically aligned with the second layering line; wherein, after the alignment, the second sub-layering line overlaps with the second layering line or is separated by a preset distance.

2. The method according to claim 1, characterized in that If the target hierarchical results include the first hierarchical results and the second hierarchical results, the display priority of the first hierarchical results is higher than the display priority of the second hierarchical results.

3. The method according to claim 2, characterized in that The first stratification result is determined by: Acquire a plurality of initial layering results for the OCT image that are pre-defined by a user; Counting the usage frequency corresponding to each of the initial stratification results; The initial stratification result with the highest usage frequency is determined as the first stratification result.

4. The method according to claim 1, characterized in that: Receiving a modification instruction for a target layering line, the step of modifying the target layering line comprises: A movement instruction for the target layer line is received, and the target layer line is modified according to the movement instruction.

5. The method according to claim 1, characterized in that Receiving a modification instruction for a target layering line, the step of modifying the target layering line comprises: receiving a displacement parameter adjustment instruction for the target layer line and determining a displacement adjustment amount; The target layering line is modified according to the displacement adjustment amount.

6. The method according to claim 1, characterized in that The OCT image includes lesion information; the second layered result is obtained by: The OCT image is input into the neural network model, and the neural network model outputs the second stratification result that matches the lesion information.

7. The method according to claim 6, characterized in that The lesion information includes at least one of the following: lesion location, lesion shape and lesion size.

8. The method according to any one of claims 1 to 7, characterized in that: The OCT image is a B-scan image or a three-dimensional image corresponding to volume data.

Images