Three-dimensional guide-based macular hole location tracking method, device, equipment, medium and product

Abstract

The application provides a macular hole position tracking method, device, equipment, medium and product based on three-dimensional guidance, and relates to the technical field of image processing. The method comprises the following steps: obtaining a fundus three-dimensional image, obtaining position information of a macular hole based on the fundus three-dimensional image, obtaining a target microscopic image, and adding the position information to the target microscopic image based on the mapping relationship between the fundus three-dimensional image and the target microscopic image. Compared with the prior art, which relies on manual observation of a two-dimensional microscopic image to determine the position information of the macular hole, the application can effectively improve the recognition accuracy of the macular hole in the microscopic image.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, apparatus, device, medium and product for 3D-guided macular hole location tracking. Background Technology

[0002] Macular hole is a fundus disease that impairs vision. It is usually caused by posterior vitreous detachment pulling on the macula, resulting in a full-thickness or partial-thickness tissue defect in the center of the macula. Surgery is the primary treatment for macular holes, typically performed under an operating microscope. However, current surgical procedures rely on surgeons directly determining the location of the macular hole from two-dimensional images under a microscope to estimate its location, and then proceeding with surgery based on this estimate. However, because the contrast between the macular hole and the surrounding image is not always significant, directly identifying the location and morphology of the macular hole based on two-dimensional fundus microscopic images under an eyepiece has considerable limitations. The accuracy of identifying the macular hole location in the microscopic image is low, affecting surgical efficiency. Summary of the Invention

[0003] This application provides a method, apparatus, device, medium, and product for tracking the location of macular holes based on three-dimensional guidance, in order to solve the defects in the accuracy of macular hole location identification in microscopic images in the prior art, and to achieve the effect of improving the accuracy of macular hole location identification in microscopic images.

[0004] This application provides a three-dimensional guided method for locating macular hole positions, including: Acquire a three-dimensional image of the fundus, and based on the three-dimensional image of the fundus, obtain the location information of the macular hole; A target microscopic image is acquired, and the location information is added to the target microscopic image based on the mapping relationship between the fundus three-dimensional image and the target microscopic image.

[0005] According to the three-dimensional guided method for macula hole location tracking provided in this application, the step of adding the location information to the target microscopic image based on the mapping relationship between the three-dimensional fundus image and the target microscopic image includes: A first mapping relationship is obtained between the three-dimensional fundus image and the reference microscopic image. Based on the first mapping relationship, the location information of the macular hole is added to the reference microscopic image to obtain an information-informed reference microscopic image. A second mapping relationship is obtained between the target microscopic image and the information-bearing reference microscopic image. Based on the second mapping relationship, the position information is added to the target microscopic image.

[0006] According to the three-dimensional guided macular hole location tracking method provided in this application, the step of obtaining the second mapping relationship between the target microscopic image and the information-bearing reference microscopic image includes: Image registration is performed between the target microscopic image and the reference microscopic image to obtain the image registration result; Based on the image registration results, the second mapping relationship is determined.

[0007] According to the three-dimensional guided method for locating the macular hole provided in this application, the method for obtaining the location information of the macular hole based on the three-dimensional fundus image includes: The three-dimensional image of the fundus is projected to generate a projected image of the fundus; The location information is extracted based on the projected image.

[0008] According to the three-dimensional guided method for locating macular holes provided in this application, the step of extracting the location information based on the projected image includes: The macular hole boundary is segmented on the projected image to obtain a binary mask of the macular hole; The location information is obtained based on the binary mask.

[0009] According to the method for tracking the location of macular holes based on three-dimensional guidance provided in this application, the location information of the macular holes includes surgical range information for the macular holes.

[0010] This application also provides a three-dimensional guided macular hole location tracking device, comprising: The location information acquisition module is used to acquire a three-dimensional image of the fundus and obtain the location information of the macular hole based on the three-dimensional image of the fundus. The location information adding module is used to acquire the target microscopic image and add the location information to the target microscopic image based on the mapping relationship between the fundus three-dimensional image and the target microscopic image.

[0011] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the three-dimensional guided macular hole location tracking method as described above.

[0012] This application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the three-dimensional guided macular hole location tracking method as described above.

[0013] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the three-dimensional guided macular hole location tracking method as described above.

[0014] The method, apparatus, device, medium, and product for 3D-guided macular hole location tracking provided in this application first acquire a 3D fundus image, then obtain the location information of the macular hole based on the 3D fundus image. After acquiring a target microscopic image, the location information is added to the target microscopic image based on the mapping relationship between the 3D fundus image and the target microscopic image. In this way, comprehensive location information of the macular hole can be obtained based on the 3D fundus image, improving the accuracy of the location information of the macular hole. Then, the location information is added to the target microscopic image based on the mapping relationship between the 3D fundus image and the target microscopic image. Compared with the prior art that relies on manual observation of 2D microscopic images to determine the location information of the macular hole, this method can effectively improve the recognition accuracy of the macular hole in the microscopic image. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating the three-dimensional guided method for locating macular holes provided in this application.

[0017] Figure 2 This is a schematic diagram illustrating the dynamic addition process of digital markers for macular hole locations in one embodiment of the three-dimensional guided macular hole location tracking method provided in this application.

[0018] Figure 3 This is a schematic diagram of a three-dimensional fundus image in the three-dimensional guided macular hole location tracking method provided in this application.

[0019] Figure 4 This is a schematic diagram of the projected image in the three-dimensional guided macular hole location tracking method provided in this application.

[0020] Figure 5 This is a schematic diagram of the macular hole binary mask in the three-dimensional guided macular hole location tracking method provided in this application.

[0021] Figure 6 This is a schematic diagram of a target microscopic image with location information in the three-dimensional guided macular hole location tracking method provided in this application.

[0022] Figure 7 This is a schematic diagram of dynamically superimposing position information in continuous microscopic images in the three-dimensional guided macular hole location tracking method provided in this application.

[0023] Figure 8 This is a schematic diagram of the structure of the three-dimensional guided macular hole location tracking device provided in this application.

[0024] Figure 9 This is a schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0027] It should also be understood that the terminology used in this application specification is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this application specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0028] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0029] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0030] The following is combined with Figures 1-7This application describes a three-dimensional guided method for locating macular hole positions. For example... Figure 1 As shown, the three-dimensional guided method for locating macular hole positions includes the following steps: S110. Obtain a three-dimensional image of the fundus, and based on the three-dimensional image of the fundus, obtain the location information of the macular hole; S120. Acquire the target microscopic image, and add the location information to the target microscopic image based on the mapping relationship between the fundus three-dimensional image and the target microscopic image.

[0031] The device that performs the three-dimensional guided macular hole location tracking method provided in this application can be a device that is communicatively connected to a microscopic imaging device. This device obtains the location information of the macular hole based on a three-dimensional fundus image in real time during the operation or in advance before the operation. During the operation, the target microscopic image is transmitted to the device that performs the three-dimensional guided macular hole location tracking method provided in this application. The device adds the location information to the target microscopic image. In this way, a microscopic image with macular hole location information can be displayed, providing reference and guidance information for the surgical operation. The surgeon can refer to the microscopic image to perform the operation.

[0032] The 3D-guided macular hole location tracking method provided in this application first acquires a 3D fundus image, then obtains the location information of the macular hole based on the 3D fundus image. After acquiring the target microscopic image, the location information is added to the target microscopic image based on the mapping relationship between the 3D fundus image and the target microscopic image. In this way, comprehensive location information of the macular hole can be obtained based on the 3D fundus image, improving the accuracy of the location information of the macular hole. Then, the location information is added to the target microscopic image based on the mapping relationship between the 3D fundus image and the target microscopic image. Compared with the existing technology that relies on manual observation of 2D microscopic images to determine the location information of the macular hole, this method can effectively improve the recognition accuracy of the macular hole in the microscopic image and improve surgical efficiency.

[0033] Three-dimensional images of the fundus can be obtained by imaging the fundus in three dimensions using techniques such as OCT (Optical Coherence Tomography). Three-dimensional images generated using OCT technology can capture subtle morphological changes in the posterior segment of the eye caused by the macular hole. Three-dimensional fundus images generated using OCT technology can, for example... Figure 3 As shown. It is understood that the three-dimensional guided macular hole location tracking method provided in this application is not limited to OCT technology to generate three-dimensional fundus images, and various existing three-dimensional imaging methods can also be used. Those skilled in the art can make flexible choices based on the actual situation.

[0034] In one possible implementation, obtaining the location information of the macular hole based on a three-dimensional fundus image can involve target recognition of the three-dimensional fundus image, extracting the three-dimensional morphology of the macular hole in the image, and thus determining the three-dimensional location information of the macular hole. Alternatively, in another possible implementation, obtaining the location information of the macular hole based on a three-dimensional fundus image can involve slicing the three-dimensional fundus image to obtain multiple two-dimensional images, and then performing macular hole recognition based on these two-dimensional images to obtain the location information of the macular hole.

[0035] The inventors discovered that in practical applications, surgery primarily considers the overall location of the macular hole, rather than requiring precise location information at different depths. Based on this, one possible implementation of the three-dimensional guided macular hole location tracking method provided in this application involves obtaining the macular hole location information based on a three-dimensional fundus image, including: Projecting a three-dimensional image of the fundus into a projected image of the fundus; Location information is extracted based on the projected image.

[0036] In this implementation, after obtaining the three-dimensional image of the fundus, an en-face image (frontal image) is generated by projection along the axial direction (z-axis) as the projection image, such as... Figure 4 As shown, projection methods for projecting three-dimensional images of the fundus include, but are not limited to, maximum density projection and average density projection.

[0037] By projecting a three-dimensional image of the fundus to generate a projected image of the fundus, and then extracting the location information of the macular hole based on this projected image, the extraction efficiency of the location information of the macular hole can be improved.

[0038] After obtaining the projected image, the location information of the macular hole can be extracted from the projected image, specifically including: The macular hole boundary is segmented on the projected image to obtain a binary mask of the macular hole; Location information is obtained based on a binary mask.

[0039] In the application scenario of this application, it is only necessary to obtain the position and shape of the macular hole in the fundus, and the specific pixel information inside the macular hole is not needed. Therefore, only the binary mask of the macular hole is extracted, which reduces the complexity of extracting the position information.

[0040] In one possible implementation, the macular hole boundary is segmented on the projected image to obtain a binary mask for the macular hole. This can be achieved by combining image gradient intensity with boundary segmentation methods, or by directly inferring the macular hole binary mask using a pre-trained convolutional neural network deep learning model. Specifically, obtaining the macular hole binary mask based on image gradient intensity combined with boundary segmentation methods is a classic edge detection-driven image segmentation technique. Its core idea is to use pixel gradient magnitude to reflect edge intensity and treat strong edge pixels as object boundaries by setting thresholds or linking strategies, thereby achieving image segmentation. The method of directly inferring the macular hole binary mask using a pre-trained convolutional neural network deep learning model involves pre-constructing multiple sets of training data. Each set of training data includes sample projected images and corresponding macular hole binary mask labels. The model is trained based on this training data, enabling it to output a binary mask of the macular hole in the image based on the input image. Of course, it is understood that the three-dimensional guided macular hole location tracking method provided in this application does not limit the specific implementation of extracting the binary mask of the macular hole from the projection image. Those skilled in the art can flexibly choose existing methods for extracting the binary mask of the target object from the image to extract the binary mask of the macular hole in the projection image based on the actual situation.

[0041] The extracted binary mask for macular holes can be used as follows: Figure 5 As shown.

[0042] Based on a binary mask of the macular hole, the boundary position and morphology of the macular hole in the projected image can be determined; this information constitutes the location information of the macular hole. When adding this location information to the microscopic image, it can be done by adding digital markers reflecting the location information. In one possible implementation, the location information may only include the boundary position and morphology of the macular hole, such as... Figure 6 As shown in the red circle, in another possible implementation, the location information may also include surgical extent information for the macular hole generated based on the boundary location and boundary morphology, such as... Figure 6 As shown in the yellow circle. Specifically, the surgical extent information for the macular hole can be a fixed-size circular area generated with the center of the macular hole as a guide for the surgical extent. By generating surgical extent information for the macular hole and adding it to the location information of the macular hole, and further adding the location information to the microscopic image, more reference and guidance information can be provided for the surgical operation, which helps to improve surgical efficiency.

[0043] After obtaining the location information of the macular hole, a target microscopic image is acquired. Based on the mapping relationship between the fundus 3D image and the target microscopic image, the location information is added to the target microscopic image.

[0044] Since the location information of the macular hole is extracted from a three-dimensional fundus image, and the three-dimensional fundus image and the target microscopic image may have different imaging positions, imaging angles, and imaging sizes, the location information of the macular hole in the three-dimensional fundus image cannot be directly applied to the two-dimensional microscopic image. In one possible implementation, a direct mapping relationship between the three-dimensional fundus image and the target microscopic image can be obtained, and the location information can be added to the target microscopic image. Obtaining the mapping relationship between the three-dimensional and two-dimensional images is relatively difficult. In practical applications, the microscopic imaging device may be moved during surgery, causing the microscopic image to change continuously. Obtaining the direct mapping relationship between the three-dimensional fundus image and the microscopic image each time would result in high computational complexity. In another possible implementation of the three-dimensional guided macular hole location tracking method provided in this application, the location information is added to the target microscopic image based on the mapping relationship between the three-dimensional fundus image and the target microscopic image, including: Obtain the first mapping relationship between the three-dimensional image of the fundus and the reference microscopic image. Based on the first mapping relationship, add the location information of the macular hole to the reference microscopic image to obtain the reference microscopic image with information. A second mapping relationship is obtained between the target microscopic image and the information-bearing reference microscopic image. Based on the second mapping relationship, positional information is added to the target microscopic image.

[0045] The first mapping relationship between the three-dimensional fundus image and the reference microscopic image reflects the correspondence between pixels in the three-dimensional fundus image and pixels in the reference microscopic image. If the two correspond to the same point of an actual object, then the pixels in the two images are said to have a correspondence. The second mapping relationship between the target microscopic image and the information-bearing reference microscopic image reflects the correspondence between pixels in the target microscopic image and pixels in the information-bearing reference microscopic image.

[0046] In this implementation, a microscopic image is selected as a reference microscopic image. First, the first mapping relationship between the reference microscopic image and the three-dimensional fundus image is obtained. The location information of the macular hole extracted based on the three-dimensional fundus image is added to the reference microscopic image to obtain an information-bearing reference microscopic image. For target microscopic images other than the reference microscopic image, only the second mapping relationship between the target microscopic image and the information-bearing reference microscopic image needs to be obtained. Based on the second mapping relationship, the location information in the information-bearing reference microscopic image is added to the target microscopic image. For example, the numerical markers in the information-bearing reference microscopic image are added to the target microscopic image.

[0047] In one possible implementation, such as Figure 2 As shown, an initial microscopic planar image can be acquired as a reference microscopic image while the fundus 3D scanning is started to generate a fundus 3D image. At this time, the fundus position corresponding to the imaging of the fundus 3D image and the imaging of the reference microscopic image does not change. In this way, the first mapping relationship between the fundus 3D image and the reference microscopic image can be obtained based on the 3D scanning position and the imaging position of the microscopic reference image. After the position information of the macular hole is extracted based on the fundus 3D image, the position information of the macular hole is added to the reference microscopic image to obtain an information-informed reference microscopic image.

[0048] In one possible implementation of the three-dimensional guided macular hole location tracking method provided in this application, the second mapping relationship between the target microscopic image and the information-bearing reference microscopic image can be determined based on the position of the microscopic imaging device when generating the target microscopic image and the reference microscopic image. However, during imaging, the patient's position may change, i.e., the position of the fundus, which is the imaging object, may change. This method of directly determining the second mapping relationship based on the position of the microscopic imaging device carries the risk of inaccurate results. To address this deficiency, in another possible implementation of the three-dimensional guided macular hole location tracking method provided in this application, obtaining the second mapping relationship between the target microscopic image and the information-bearing reference microscopic image includes: Image registration is performed between the target microscopic image and the reference microscopic image to obtain the image registration result; Based on the image registration results, a second mapping relationship is determined.

[0049] In this implementation, the target microscopic image and the reference microscopic image are image registered to obtain the image registration result, and the second mapping relationship is determined based on the image registration result.

[0050] Image registration between the target microscopic image and the reference microscopic image can be achieved using existing image registration techniques. Obtaining a second mapping relationship between the target and reference microscopic images through image registration avoids inaccuracies in the second mapping relationship caused by changes in the fundus position during surgery, thus improving the accuracy of the second mapping relationship and consequently enhancing the accuracy of the macular hole location information added to the target microscopic image.

[0051] The three-dimensional guided macular hole location tracking method provided in this application allows each frame in the video stream generated by the movement of the microscopic imaging device during surgery to be considered as a target microscopic image, such as... Figure 2As shown, the reference microscopic image can be considered as frame 0. Based on the second mapping relationship between the target microscopic image and the information-bearing reference microscopic image, positional information is added to the target microscopic image to achieve positional tracking of the macular hole in the video stream, as shown. Figure 7 As shown.

[0052] The following describes the three-dimensional guided macular hole location tracking device provided in this application. The three-dimensional guided macular hole location tracking device described below can be referred to in correspondence with the three-dimensional guided macular hole location tracking method described above. Figure 8 As shown, the three-dimensional guided macular hole location tracking device provided in this application includes: The location information acquisition module 810 is used to acquire three-dimensional images of the fundus and obtain the location information of the macular hole based on the three-dimensional images of the fundus. The location information adding module 820 is used to acquire the target microscopic image and add location information to the target microscopic image based on the mapping relationship between the fundus three-dimensional image and the target microscopic image.

[0053] The 3D-guided macular hole location tracking device provided in this application first acquires a 3D fundus image, and then obtains the location information of the macular hole based on the 3D fundus image. After acquiring a target microscopic image, the location information is added to the target microscopic image based on the mapping relationship between the 3D fundus image and the target microscopic image. In this way, comprehensive location information of the macular hole can be obtained based on the 3D fundus image, improving the accuracy of the location information of the macular hole. Then, the location information is added to the target microscopic image based on the mapping relationship between the 3D fundus image and the target microscopic image. Compared with the existing technology that relies on manual observation of 2D microscopic images to determine the location information of the macular hole, this device can effectively improve the recognition accuracy of the macular hole in the microscopic image.

[0054] In one possible implementation of the three-dimensional guided macular hole location tracking device provided in this application, the location information is added to the target microscopic image based on the mapping relationship between the three-dimensional fundus image and the target microscopic image, including: A first mapping relationship is obtained between the three-dimensional fundus image and the reference microscopic image. Based on the first mapping relationship, the location information of the macular hole is added to the reference microscopic image to obtain an information-informed reference microscopic image. A second mapping relationship is obtained between the target microscopic image and the information-bearing reference microscopic image. Based on the second mapping relationship, the position information is added to the target microscopic image.

[0055] In one possible implementation of the three-dimensional guided macular hole location tracking device provided in this application, the step of acquiring the second mapping relationship between the target microscopic image and the information-bearing reference microscopic image includes: Image registration is performed between the target microscopic image and the reference microscopic image to obtain the image registration result; Based on the image registration results, the second mapping relationship is determined.

[0056] In one possible implementation of the three-dimensional guided macular hole location tracking device provided in this application, obtaining the location information of the macular hole based on the three-dimensional fundus image includes: The three-dimensional image of the fundus is projected to generate a projected image of the fundus; The location information is extracted based on the projected image.

[0057] In one possible implementation of the three-dimensional guided macular hole location tracking device provided in this application, the step of extracting the location information based on the projected image includes: The macular hole boundary is segmented on the projected image to obtain a binary mask of the macular hole; The location information is obtained based on the binary mask.

[0058] In one possible implementation of the three-dimensional guided macular hole location tracking device provided in this application, the location information of the macular hole includes surgical range information for the macular hole.

[0059] Figure 9 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 9 As shown, the electronic device may include a processor 910, a communications interface 920, a memory 930, and a communication bus 940. The processor 910, communications interface 920, and memory 930 communicate with each other via the communication bus 940. The processor 910 can call logical instructions in the memory 930 to execute a three-dimensional guided macular hole location tracking method. This three-dimensional guided macular hole location tracking method includes: acquiring a three-dimensional fundus image; obtaining the location information of the macular hole based on the three-dimensional fundus image; acquiring a target microscopic image; and adding the location information to the target microscopic image based on the mapping relationship between the three-dimensional fundus image and the target microscopic image.

[0060] Furthermore, the logical instructions in the aforementioned memory 930 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0061] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the three-dimensional guided macular hole location tracking method provided by the above methods. This three-dimensional guided macular hole location tracking method includes: acquiring a three-dimensional fundus image; obtaining the location information of the macular hole based on the three-dimensional fundus image; acquiring a target microscopic image; and adding the location information to the target microscopic image based on the mapping relationship between the three-dimensional fundus image and the target microscopic image.

[0062] Furthermore, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the three-dimensional guided macular hole location tracking method provided by the above methods. This three-dimensional guided macular hole location tracking method includes: acquiring a three-dimensional fundus image; obtaining the location information of the macular hole based on the three-dimensional fundus image; acquiring a target microscopic image; and adding the location information to the target microscopic image based on the mapping relationship between the three-dimensional fundus image and the target microscopic image.

[0063] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0064] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0065] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for locating macular hole positions based on three-dimensional guidance, characterized in that, include: Acquire a three-dimensional image of the fundus, and based on the three-dimensional image of the fundus, obtain the location information of the macular hole; A target microscopic image is acquired, and the location information is added to the target microscopic image based on the mapping relationship between the fundus three-dimensional image and the target microscopic image.

2. The method for locating macular holes based on three-dimensional guidance according to claim 1, characterized in that, The step of adding the location information to the target microscopic image based on the mapping relationship between the fundus three-dimensional image and the target microscopic image includes: A first mapping relationship is obtained between the three-dimensional fundus image and the reference microscopic image. Based on the first mapping relationship, the location information of the macular hole is added to the reference microscopic image to obtain an information-informed reference microscopic image. A second mapping relationship is obtained between the target microscopic image and the information-bearing reference microscopic image. Based on the second mapping relationship, the position information is added to the target microscopic image.

3. The method for locating macular holes based on three-dimensional guidance according to claim 2, characterized in that, The step of obtaining the second mapping relationship between the target microscopic image and the information-bearing reference microscopic image includes: Image registration is performed between the target microscopic image and the reference microscopic image to obtain the image registration result; Based on the image registration results, the second mapping relationship is determined.

4. The method for locating macular holes based on three-dimensional guidance according to claim 1, characterized in that, The process of obtaining the location information of the macular hole based on the three-dimensional fundus image includes: The three-dimensional image of the fundus is projected to generate a projected image of the fundus; The location information is extracted based on the projected image.

5. The method for locating macular hole based on three-dimensional guidance according to claim 4, characterized in that, Extracting the location information based on the projected image includes: The macular hole boundary is segmented on the projected image to obtain a binary mask of the macular hole; The location information is obtained based on the binary mask.

6. The method for locating macular holes based on three-dimensional guidance according to claim 1, characterized in that, The location information of the macular hole includes information on the surgical extent for the macular hole.

7. A three-dimensional guided macular hole location tracking device, characterized in that, include: The location information acquisition module is used to acquire a three-dimensional image of the fundus and obtain the location information of the macular hole based on the three-dimensional image of the fundus. The location information adding module is used to acquire the target microscopic image and add the location information to the target microscopic image based on the mapping relationship between the fundus three-dimensional image and the target microscopic image.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the three-dimensional guided macular hole location tracking method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the three-dimensional guided macular hole location tracking method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the three-dimensional guided macular hole location tracking method as described in any one of claims 1 to 6.

Images