Visualization method and device for fundus focus and computer readable medium

Abstract

The invention provides a fundus focus visualization method and device and a computer readable medium, and the method comprises the steps: carrying out the abnormal region detection of a target fundus image, and obtaining a detection result; if the detection result shows that an abnormal region with an obvious boundary exists in the target fundus image, determining a visualization mode corresponding to a focus based on feature parameters corresponding to the focus of the abnormal region; and according to the visualization mode corresponding to each focus, performing visualization display on the abnormal region corresponding to the focus in the target fundus image, and generating a focus visualization result. According to the embodiment of the invention, the visual mode of determining the abnormal area corresponding to the focus according to the focus severity can be realized, so that the accuracy of fundus abnormality diagnosis is improved; and a doctor can be helped to more intuitively explain serious conditions of fundus abnormality to a patient, so that the patient can better understand own illness conditions, and the effectiveness of doctor-patient communication is enhanced.

Description

Technical Field

[0001] This invention belongs to the field of image processing technology, and in particular relates to a method, apparatus and computer-readable medium for visualizing fundus lesions. Background Technology

[0002] Fundus abnormalities refer to a wide range of abnormalities occurring in various structures of the eye. The main symptoms include decreased vision, distorted vision, visual field defects, floaters, pain, and photophobia.

[0003] Current technologies only display single-disease abnormalities in the fundus, lacking a method for labeling all fundus abnormalities. This is primarily because multiple fundus lesions may coexist and influence each other, potentially leading to unclear labeling. Even if current technologies can label various fundus abnormalities manually, the labeling results for the same fundus image can still vary significantly due to the influence of different doctors' experience.

[0004] Therefore, there is an urgent need to provide a visualization method for fundus lesions to solve the technical problem that the limitations of existing technology prevent patients or medical staff in other departments from having a clear and intuitive understanding of fundus lesions. Summary of the Invention

[0005] To address the aforementioned problems in the existing technology, embodiments of the present invention provide a method, apparatus, and computer-readable medium for visualizing fundus lesions. This method can visually display fundus abnormalities according to the severity of fundus lesions, improving the accuracy of fundus abnormality diagnosis.

[0006] According to a first aspect of the present invention, a method for visualizing fundus lesions is provided. The method includes: detecting abnormal regions in a target fundus image to obtain detection results; if the detection results indicate that there are abnormal regions with obvious boundaries in the target fundus image, determining a visualization method corresponding to the lesion based on the feature parameters corresponding to the lesion in the abnormal region; and visualizing the abnormal regions corresponding to the lesions in the target fundus image according to the visualization method corresponding to each lesion to generate a lesion visualization result.

[0007] Optionally, the step of detecting abnormal regions in the target fundus image to obtain a detection result includes: detecting abnormal regions in the target fundus image to obtain a first detection result; if the first detection result indicates that there is an abnormal region in the target fundus image, then performing localization processing on the abnormal region to obtain a localization result; and performing edge detection on the abnormal region based on the localization result to obtain a second detection result.

[0008] Optionally, the method further includes: determining the lesion type corresponding to the abnormal region; and determining the characteristic parameters of the lesion corresponding to the abnormal region based on the lesion type.

[0009] Optionally, determining the visualization method corresponding to the lesion based on the feature parameters corresponding to the lesion in the abnormal region includes: determining whether the feature parameters meet a first preset condition; if the feature parameters meet the first preset condition, determining the display color and a first visualization method corresponding to the lesion, wherein the first visualization method is used to instruct the abnormal region to be rendered with the display color based on the boundary of the abnormal region; if the feature parameters do not meet the first preset condition, determining the display color and a second visualization method corresponding to the lesion; wherein the second visualization method is used to instruct the abnormal region to be displayed with a heatmap based on the feature parameters and the display color.

[0010] Optionally, the step of determining the display color and second visualization method corresponding to the lesion if the feature parameters do not meet the first preset condition includes: determining the display color corresponding to the lesion if the feature parameters do not meet the first preset condition; establishing a mapping relationship between the feature parameters, the probability of the lesion, and the display color pixels; and determining the heat map display method corresponding to the lesion based on the mapping relationship, and generating the second visualization method.

[0011] Optionally, determining the characteristic parameters of the lesion corresponding to the abnormal region based on the lesion type includes: determining the lesion parameters corresponding to the abnormal region based on the lesion type; if there are at least two lesion parameters, then selecting the key parameter corresponding to the lesion from the at least two lesion parameters as the characteristic parameter; or, determining the weight corresponding to each lesion parameter, applying the corresponding weight to the at least two lesion parameters, and performing weighted processing to generate the characteristic parameter of the lesion; if there is only one lesion parameter, then using the lesion parameter as the characteristic parameter of the lesion.

[0012] Optionally, the method further includes: if the detection result indicates that there is an abnormal region in the target fundus image and the boundary of the abnormal region is not obvious, then the lesion corresponding to the abnormal region in the target fundus image is visualized by means of a heat map to generate a lesion visualization result.

[0013] According to a second aspect of the present invention, a visualization device for fundus lesions is also provided. The device includes: a detection module for detecting abnormal regions in a target fundus image and obtaining a detection result; a first determination module for determining a visualization method corresponding to the lesion based on feature parameters corresponding to the lesion in the abnormal region if the detection result indicates that there is an abnormal region with obvious boundaries in the target fundus image; and a visualization module for visualizing the abnormal region corresponding to the lesion in the target fundus image according to the visualization method corresponding to each lesion, and generating a lesion visualization result.

[0014] Optionally, the visualization module includes: a determining unit, configured to determine whether the feature parameters satisfy a first preset condition; a first generating unit, configured to determine the display color and a first visualization method corresponding to the lesion if the feature parameters satisfy the first preset condition, wherein the first visualization method is used to instruct the display color of the abnormal region based on the boundary of the abnormal region; and a second generating unit, configured to determine the display color and a second visualization method corresponding to the lesion if the feature parameters do not satisfy the first preset condition, wherein the second visualization method is used to instruct the display of a heatmap of the abnormal region based on the feature parameters and the display color.

[0015] According to a third aspect of the present invention, an electronic device is also provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method as described in the first aspect.

[0016] According to a fourth aspect of the present invention, a computer-readable medium is also provided, on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in the first aspect.

[0017] This invention provides a method, apparatus, and computer-readable medium for visualizing fundus lesions. The method includes: detecting abnormal regions in a target fundus image to obtain detection results; if the detection results indicate the presence of clearly defined abnormal regions in the target fundus image, determining a visualization method corresponding to the lesion based on feature parameters corresponding to the lesion in the abnormal region; and visualizing the abnormal regions corresponding to the lesions in the target fundus image according to the visualization method corresponding to each lesion, generating a lesion visualization result. In this embodiment, after identifying fundus abnormalities, the visualization method of the lesion is determined based on the feature parameters of the lesions corresponding to the abnormal regions, and abnormal regions corresponding to the same type of lesions in the target fundus image are displayed in the same form based on the visualization method of the lesions. Therefore, it is possible to determine the visualization method of the abnormal regions corresponding to the lesions based on the severity of the lesions, thereby not only reducing errors caused by subjective human factors and improving the accuracy of fundus abnormality diagnosis, but also helping doctors to explain the severity of fundus abnormalities to patients more intuitively, helping patients better understand their condition, and enhancing the effectiveness of doctor-patient communication. Attached Figure Description

[0018] The following sections will describe some specific embodiments of the invention in a detailed manner by way of example and not limitation, with reference to the accompanying drawings. The same reference numerals in the drawings denote the same or similar parts or portions. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings: Figure 1 This is a flowchart illustrating a method for visualizing fundus lesions according to an embodiment of the present invention. Figure 2 Figure 1 shows a rendering (Figure a) generated by a first visualization method and a heatmap (Figure b) generated by a second visualization method corresponding to bleeding in one embodiment of the present invention. Figure 3 Figure a shows a target fundus image (Figure a) and a heat map (Figure b) of the abnormal area corresponding to the leopard spots in the target fundus, according to an embodiment of the present invention. Figure 4 This is a schematic diagram of the structure of a visualization device for fundus lesions provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0020] like Figure 1 The diagram shown is a flowchart illustrating a visualization method for fundus lesions provided in an embodiment of the present invention.

[0021] A method for visualizing fundus lesions, the method comprising at least the following steps: S101, Perform abnormal region detection on the target fundus image and obtain the detection results; S102, If the detection result indicates that there is an abnormal region with obvious boundaries in the target fundus image, then the visualization method corresponding to the lesion is determined based on the feature parameters corresponding to the lesion in the abnormal region. S103, according to the visualization method corresponding to each lesion, visualize the abnormal area corresponding to the lesion in the target fundus image and generate lesion visualization results.

[0022] In S101, "abnormal area" refers to an area formed by fundus abnormalities or non-fundus abnormalities; "fundus abnormality" refers to fundus abnormalities caused by congenital lesions, myopia, non-myopia, or human intervention. In other words, "abnormal area" refers to a fundus abnormality area or a non-fundus abnormality area; "fundus abnormality area" refers to a congenital lesion area, a myopia area, a non-myopia area, or a human intervention area.

[0023] Abnormal regions in the target fundus image are detected based on a model or preset rules to obtain detection results. For example, abnormal region detection is performed on the target fundus image to obtain a first detection result.

[0024] If the first detection result indicates the presence of an abnormal region in the target fundus image, the abnormal region is located to obtain a localization result; based on the localization result, edge detection is performed on the abnormal region to obtain a second detection result. If the first detection result indicates the absence of an abnormal region in the target fundus image, fundus structures in the target fundus image are identified to generate an identification result; wherein, the fundus structures include, but are not limited to, the optic disc, macula, and fundus vessels. If the first detection result indicates the presence of an abnormal region in the target fundus image and the second detection result indicates that the boundary of the abnormal region is indistinct, and the lesion type corresponding to the abnormal region cannot be accurately identified, the lesion corresponding to the abnormal region in the target fundus image is visualized using a heatmap to generate a lesion visualization result. Lesions corresponding to abnormal regions with indistinct boundaries typically include: optic disc edema, myelinated discs, neovascularization, or vascular sheaths.

[0025] In steps S102 and S103, after identifying a clearly defined abnormal region in the target fundus image, the lesion type corresponding to the abnormal region is identified, and based on the identified lesion type, the feature parameters of the lesion corresponding to the abnormal region are determined. Based on preset rules or models, the visualization method corresponding to the abnormal region is determined according to the lesion's feature parameters. For example, when the lesion corresponding to the abnormal region is hemorrhage, the feature parameters corresponding to hemorrhage include the hemorrhage area and the amount of hemorrhage; if the amount of hemorrhage is less than a first preset threshold and the hemorrhage area is not less than a second preset threshold, then the abnormal region is determined to correspond to a first visualization method; if the amount of hemorrhage is less than the first preset threshold and the hemorrhage area is greater than the second preset threshold, then the abnormal region is determined to correspond to a second visualization method.

[0026] For example, firstly, based on the lesion type, lesion parameters corresponding to the abnormal region are determined; if there are at least two lesion parameters, a key parameter corresponding to the lesion is selected from the at least two lesion parameters as a feature parameter; or, a weight corresponding to each lesion parameter is determined, the corresponding weight is applied to the at least two lesion parameters, and weighted processing is performed to generate the feature parameter of the lesion; if there is only one lesion parameter, the lesion parameter is used as the feature parameter of the lesion. Secondly, it is determined whether the feature parameter meets a first preset condition; if the feature parameter meets the first preset condition, the display color and first visualization method corresponding to the lesion are determined, wherein the first visualization method is used to instruct the display color of the abnormal region based on the boundary of the abnormal region; if the feature parameter does not meet the first preset condition, the display color and second visualization method corresponding to the lesion are determined; wherein the second visualization method is used to instruct the heat map display of the abnormal region based on the feature parameter and the display color.

[0027] Furthermore, the step of determining the display color and second visualization method corresponding to the lesion if the feature parameters do not meet the first preset condition includes: determining the display color corresponding to the lesion if the feature parameters do not meet the first preset condition; establishing a mapping relationship between the feature parameters, the probability of the lesion, and the display color pixels; and determining the heat map display method corresponding to the lesion based on the mapping relationship, and generating the second visualization method.

[0028] like Figure 2 As shown, these are a rendering (Figure a) generated by the first visualization method and a heat map (Figure b) generated by the second visualization method corresponding to bleeding in one embodiment of the present invention.

[0029] For example, when the lesion type in the abnormal area is hemorrhage, the corresponding lesion parameters include: hemorrhage area, number of hemorrhages, distribution pattern, and density. Hemorrhage area and number of hemorrhages are selected as feature parameters from these parameters. If the number of hemorrhages is less than a first preset threshold and there are no hemorrhages with an area greater than a second preset threshold, it indicates that the feature parameters meet the first preset condition. In this case, the display color for the hemorrhage is determined to be green, and the rendering color display method is set. Then, based on the boundary of the abnormal area, the abnormal area is rendered green to generate a rendering image, as shown in Figure a. If the number of hemorrhages is less than the first preset threshold and there are hemorrhages with an area greater than the second preset threshold, it indicates that the feature parameters do not meet the first preset condition. In this case, the display color for the hemorrhage is determined to be red. A mapping relationship is established between the hemorrhage area, the probability of the lesion, and the display color pixels. Based on this mapping relationship, the abnormal area is visualized using a heatmap, as shown in Figure b. The heatmap is a gradient map, and the intensity of the colors displayed in the heatmap indicates the probability of the lesion. The larger the area of ​​the same color, the larger the lesion area.

[0030] Here, the lesion type can also be atrophic arc, hole, silicone oil, microaneurysm, drusen, laser spot, or exudation, etc.

[0031] Figure 3 Figure 1 shows a target fundus image (Figure a) and a heat map (Figure b) of the abnormal area corresponding to the leopard spots in the target fundus, according to an embodiment of the present invention.

[0032] When the lesion type in the abnormal area is leopard spot, the lesion parameter corresponding to the abnormal area is leopard spot density (i.e., the exposed choroidal area per unit fundus area). Since there is only one lesion parameter, leopard spot density is used as the characteristic parameter of the leopard spot. Because the characteristic parameter is greater than the preset leopard spot density, the display color corresponding to the lesion is determined. A mapping relationship is established between leopard spot density, lesion probability, and display color pixels; based on the mapping relationship, the abnormal area is visualized using a heatmap. The heatmap visualizes leopard spot density using different colors. The redder the color, the greater the leopard spot density in the abnormal area, and the more severe the leopard spot; the lighter the color or the more bluish it is, the smaller the leopard spot density corresponding to the abnormal area, indicating that the leopard spot-like change in the fundus is mild, or even non-existent. In this case, the visualized heatmap indirectly reflects the severity of fundus changes by using color to represent numerical values.

[0033] Here, the lesion type can also be pigmentary degeneration, large-area venous obstruction hemorrhage, nerve fiber defects, etc.

[0034] This embodiment identifies fundus abnormalities and determines the visualization method of the lesion based on the characteristic parameters of the lesion corresponding to the abnormal area. Based on the visualization method of the lesion, the abnormal areas corresponding to the same type of lesion in the target fundus image are displayed in the same form. Thus, it is possible to determine the visualization method of the abnormal area corresponding to the lesion based on the severity of the lesion, thereby intuitively displaying the severity of the abnormal area in the target fundus image. This not only reduces the error caused by human subjective factors and improves the accuracy of fundus abnormality diagnosis, but also helps doctors to explain the severity of fundus abnormalities to patients more intuitively, helping patients better understand their condition and enhancing the effectiveness of doctor-patient communication.

[0035] In addition, the method in this embodiment is implemented through automated software, which greatly simplifies the diagnostic process, improves work efficiency, and reduces the workload of doctors.

[0036] The visualization method for fundus lesions provided in this embodiment will be described in detail below with reference to specific application scenarios.

[0037] A method for visualizing fundus lesions includes at least the following steps: S1, perform abnormal region detection on the target fundus image to obtain a first detection result; if the first detection result indicates that there is an abnormal region in the target fundus image, then execute S2; if the first detection result indicates that there is no abnormal region in the target fundus image, then execute S10.

[0038] S2 performs localization and lesion identification processing on abnormal areas to obtain localization results and lesion types.

[0039] S3, based on the lesion type, determines the lesion parameters corresponding to the abnormal area.

[0040] S4. If there are at least two lesion parameters, then select the key parameter corresponding to the lesion as the feature parameter from the at least two lesion parameters; or, determine the weight corresponding to each lesion parameter, apply the corresponding weight to the at least two lesion parameters, and perform weighted processing to generate the feature parameters of the lesion.

[0041] S5. If there is only one lesion parameter, then the lesion parameter shall be used as the characteristic parameter of the lesion.

[0042] S6, perform edge detection on the abnormal region based on the localization result to obtain a second detection result. If the second detection result indicates that there is an abnormal region with obvious boundaries in the target fundus image, then proceed to S7; if the second detection result indicates that the boundaries of the abnormal region in the target fundus image are not obvious, then proceed to S9.

[0043] S7, determine whether the feature parameters meet the first preset condition; if the feature parameters meet the first preset condition, determine the display color and first visualization method corresponding to the lesion, wherein the first visualization method is used to indicate that the display color is rendered on the abnormal area based on the boundary of the abnormal area; if the feature parameters do not meet the first preset condition, determine the display color corresponding to the lesion; establish a mapping relationship between the feature parameters, the probability of the lesion and the display color pixels; based on the mapping relationship, determine the heat map display method corresponding to the lesion and generate a second visualization method; wherein the second visualization method is used to indicate that the abnormal area is displayed on a heat map based on the feature parameters and the display color.

[0044] S8. According to the visualization method corresponding to each lesion, the abnormal area corresponding to the lesion in the target fundus image is visualized and the lesion visualization result is generated.

[0045] S9 visualizes the lesions corresponding to abnormal areas in the target fundus image using a heatmap, generating a lesion visualization result.

[0046] S10: Identify fundus structures in the target fundus image and generate identification results.

[0047] This embodiment utilizes automated software, significantly simplifying the diagnostic process, improving efficiency, and reducing the workload of doctors. The use of different colors to visually indicate the severity of abnormalities helps doctors develop more precise treatment plans, providing strong support for patient care. This method is not only applicable to clinical diagnosis but can also serve as a teaching tool, helping ophthalmologists and students better understand and master the characteristics of fundus abnormalities. Furthermore, this method facilitates telemedicine services, enabling remote doctors to quickly and accurately assess a patient's fundus condition by remotely transmitting color-coded fundus images.

[0048] It should be understood that, in the various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0049] like Figure 4 The diagram shown is a schematic representation of a visualization device for fundus lesions provided in an embodiment of the present invention.

[0050] A visualization device for fundus lesions, the device 400 comprising at least the following steps: a detection module 401, configured to detect abnormal regions in a target fundus image and obtain detection results; a first determination module 402, configured to determine the visualization method corresponding to the lesion based on the feature parameters corresponding to the lesion in the abnormal region if the detection results indicate that there is an abnormal region with obvious boundaries in the target fundus image; and a visualization module 403, configured to visualize the abnormal region corresponding to the lesion in the target fundus image according to the visualization method corresponding to each lesion, and generate a lesion visualization result.

[0051] In a preferred embodiment of this example, the detection module includes: a first detection unit, used to detect abnormal regions in the target fundus image to obtain a first detection result; a localization unit, used to localize the abnormal region if the first detection result indicates that there is an abnormal region in the target fundus image to obtain a localization result; and a second detection unit, used to perform edge detection on the abnormal region based on the localization result to obtain a second detection result.

[0052] In a preferred embodiment of this invention, the device includes: a second determining module for determining the lesion type corresponding to the abnormal region; and a third determining module for determining the characteristic parameters of the lesion corresponding to the abnormal region based on the lesion type.

[0053] In a preferred embodiment of this example, the first determining module includes: a determining unit, configured to determine whether the feature parameter satisfies a first preset condition; a first generating unit, configured to determine the display color and a first visualization method corresponding to the lesion if the feature parameter satisfies the first preset condition, wherein the first visualization method is used to instruct the display color of the abnormal region based on the boundary of the abnormal region; and a second generating unit, configured to determine the display color and a second visualization method corresponding to the lesion if the feature parameter does not satisfy the first preset condition, wherein the second visualization method is used to instruct the display of a heatmap of the abnormal region based on the feature parameter and the display color.

[0054] In a preferred embodiment of this example, the second generation unit includes: a determining subunit, used to determine the display color corresponding to the lesion if the feature parameters do not meet the first preset condition; a creating subunit, used to establish a mapping relationship between the feature parameters, the probability of the lesion, and the display color pixels; and a generating subunit, used to determine the heat map display method corresponding to the lesion based on the mapping relationship, and generate a second visualization method.

[0055] In a preferred embodiment of this example, the third determining module includes: a first determining unit, configured to determine lesion parameters corresponding to the abnormal region based on the lesion type; a second determining unit, configured to select a key parameter corresponding to the lesion as a feature parameter from the at least two lesion parameters if there are at least two lesion parameters; or, to determine the weight corresponding to each lesion parameter, apply the corresponding weight to the at least two lesion parameters, and perform weighted processing to generate the feature parameters of the lesion; and a third determining unit, configured to use the lesion parameter as the feature parameter of the lesion if there is only one lesion parameter.

[0056] In a preferred embodiment of this example, the visualization module is further configured to visualize the lesion corresponding to the abnormal region in the target fundus image by means of a heat map if the detection result indicates that there is an abnormal region in the target fundus image and the boundary of the abnormal region is not obvious, thereby generating a lesion visualization result.

[0057] The above-described apparatus can execute the visualization method for fundus lesions provided in an embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the visualization method for fundus lesions. Technical details not described in detail in this embodiment can be found in the visualization method for fundus lesions provided in an embodiment of the present invention.

[0058] The present invention also provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the visualization method for fundus lesions described in the present invention.

[0059] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0060] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0061] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the methods according to the following embodiments of this application described in the "Exemplary Methods" section above.

[0062] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0063] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0064] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0065] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0066] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0067] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

[0068] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0069] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0070] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for visualizing fundus lesions, characterized in that, include: Abnormal regions are detected in the target fundus image, and the detection results are obtained; If the detection result indicates that there is an abnormal region with obvious boundaries in the target fundus image, then the visualization method corresponding to the lesion is determined based on the feature parameters corresponding to the lesion in the abnormal region; According to the visualization method corresponding to each lesion, the abnormal area corresponding to the lesion in the target fundus image is visualized and displayed to generate lesion visualization results.

2. The method according to claim 1, characterized in that, The process of detecting abnormal regions in the target fundus image and obtaining detection results includes: Abnormal regions are detected in the target fundus image to obtain the first detection result; If the first detection result indicates that there is an abnormal region in the target fundus image, then the abnormal region is localized to obtain a localization result; Based on the location result, edge detection is performed on the abnormal area to obtain a second detection result.

3. The method according to claim 1, characterized in that, Also includes: Determine the type of lesion corresponding to the abnormal area; Based on the lesion type, the characteristic parameters of the lesion corresponding to the abnormal area are determined.

4. The method according to claim 1, characterized in that, The method of determining the visualization method corresponding to the lesion based on the feature parameters corresponding to the lesion in the abnormal region includes: Determine whether the feature parameters satisfy the first preset condition; If the feature parameters satisfy the first preset condition, then the display color and the first visualization method corresponding to the lesion are determined, wherein the first visualization method is used to indicate that the display color of the abnormal region is rendered based on the boundary of the abnormal region; If the feature parameters do not meet the first preset condition, then the display color and the second visualization method corresponding to the lesion are determined; wherein, the second visualization method is used to indicate the display of the abnormal area in a heat map based on the feature parameters and the display color.

5. The method according to claim 4, characterized in that, If the feature parameters do not meet the first preset condition, then determine the display color and the second visualization method corresponding to the lesion; including: If the feature parameters do not meet the first preset condition, then the display color corresponding to the lesion is determined; Establish a mapping relationship between the feature parameters, the probability of the lesion, and the displayed color pixels; Based on the mapping relationship, the heat map display method corresponding to the lesion is determined, and a second visualization method is generated.

6. The method according to claim 3, characterized in that, The step of determining the characteristic parameters of the lesion corresponding to the abnormal region based on the lesion type includes: Based on the lesion type, determine the lesion parameters corresponding to the abnormal area; If there are at least two lesion parameters, then the key parameter corresponding to the lesion is selected from the at least two lesion parameters as the feature parameter; or, the weight corresponding to each lesion parameter is determined, the corresponding weight is applied to the at least two lesion parameters, and weighted processing is performed to generate the feature parameter of the lesion. If there is only one lesion parameter, then the lesion parameter shall be used as the characteristic parameter of the lesion.

7. The method according to claim 1, characterized in that, Also includes: If the detection result indicates that there is an abnormal region in the target fundus image and the boundary of the abnormal region is not obvious, then the lesion corresponding to the abnormal region in the target fundus image is visualized by means of a heat map to generate a lesion visualization result.

8. A visualization device for fundus lesions, characterized in that, include: The detection module is used to detect abnormal regions in the target fundus image and obtain the detection results; The first determining module is used to determine the visualization method corresponding to the lesion based on the feature parameters corresponding to the lesion in the abnormal region if the detection result indicates that there is an abnormal region with obvious boundaries in the target fundus image. The visualization module is used to visualize the abnormal area corresponding to the lesion in the target fundus image according to the visualization method corresponding to each lesion, and generate lesion visualization results.

9. The apparatus according to claim 8, characterized in that, The visualization module includes: A determining unit is used to determine whether the feature parameters satisfy a first preset condition; The first generation unit is configured to determine the display color and the first visualization method corresponding to the lesion if the feature parameters satisfy the first preset condition, wherein the first visualization method is configured to instruct the display color of the abnormal region based on the boundary of the abnormal region; The second generation unit is used to determine the display color and the second visualization method corresponding to the lesion if the feature parameters do not meet the first preset conditions; wherein the second visualization method is used to instruct the abnormal area to be displayed in a heat map based on the feature parameters and the display color.

10. A computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the method as claimed in any one of claims 1-7.

Images