Method and device for retinal image registration between subjects, electronic device, and storage medium

Abstract

The disclosed embodiments provide a method and device for retinal image registration between subjects, an electronic device, and a storage medium, and relate to the field of artificial intelligence technology. The method for retinal image registration between subjects includes: acquiring at least two original images; the original images are images of different subjects, and the original images include optical coherence tomography images of retinal en-face perspectives; the original images include source images and target images; the original images are processed by retinal thickness calculation to obtain a target thickness image; the target thickness image contains the thickness information of the retina in the original image; the target thickness image is processed by polar coordinate space transformation to obtain a polar coordinate image in polar coordinate space; the polar coordinate images are registered in polar coordinate space to obtain a target image in the original image space. The technical solution provided by the disclosed embodiments can realize the registration of retinal images for different subjects.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and device for retinal image registration between subjects, an electronic device, and a storage medium. Background Art

[0002] In medical image registration technology, current registration methods include: regional grayscale-based registration method and feature-based registration method. Among them, the regional grayscale-based registration method extracts the grayscale information (such as histogram information) in the region and uses correlation and mutual information as the objective function for registration; the feature-based registration method achieves registration by finding feature matching points. In the process of OCT (Optical Coherence Tomography) image registration of the retinal en-face perspective within the subject, a feature-based method is usually used to use retinal vascular features for registration.

[0003] The grayscale features in the regional grayscale-based registration method are easily disturbed by the speckle noise on the OCT image, resulting in poor registration effect. Although the feature-based registration method can clearly present the retinal vascular features and find matching feature points through the retinal en-face OCT image, the retinal vascular features have strong individual specificity. The retinal blood vessels of different subjects have great differences in topological structure, vascular morphology and quantity. Therefore, the current image registration method cannot perform registration for retinal images of different subjects. Summary of the invention

[0004] The main purpose of the embodiments of the present disclosure is to provide a method and device for retinal image registration between subjects, an electronic device, and a storage medium, which can realize the registration of retinal images for different subjects.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present disclosure proposes a method for retinal image registration between subjects, comprising:

[0006] Acquire at least two original images; the original images are images of different subjects, and the original images include optical coherence tomography images of retinal en-face perspective; the original images include a source image and a target image;

[0007] Performing retinal thickness calculation processing on the original image to obtain a target thickness image; the target thickness image contains retinal thickness information in the original image;

[0008] Performing polar coordinate space transformation processing on the target thickness image to obtain a polar coordinate image in the polar coordinate space;

[0009] The polar coordinate images are registered in the polar coordinate space to obtain a target image in the original image space.

[0010] In some embodiments, registering the polar coordinate image in the polar coordinate space to obtain the target image in the original image space includes:

[0011] Registering the polar coordinate image in the polar coordinate space to obtain a target sub-image in the polar coordinate space;

[0012] The target sub-image is transformed in the original image space to obtain the target image in the original image space.

[0013] In some embodiments, registering the polar coordinate image in the polar coordinate space to obtain the target image in the original image space further includes:

[0014] Registering the polar coordinate image in the polar coordinate space to obtain a first deformation vector field in the polar coordinate space;

[0015] Performing original image space transformation processing on the first deformation vector field to obtain a second deformation vector field in the original image space;

[0016] The original image is registered according to the second deformation vector field to obtain the target image.

[0017] In some embodiments, the step of performing retinal thickness calculation processing on the original image to obtain a target thickness image includes:

[0018] Performing retinal segmentation on the original image to obtain a retinal image;

[0019] Calculating the thickness of the retinal image to obtain an initial thickness image;

[0020] The initial thickness image is subjected to image preprocessing to obtain the target thickness image.

[0021] In some embodiments, performing image preprocessing on the initial thickness image to obtain the target thickness image includes:

[0022] The initial thickness image is subjected to image denoising to obtain the target thickness image.

[0023] In some embodiments, performing image preprocessing on the initial thickness image to obtain the target thickness image further includes:

[0024] The initial thickness image is subjected to image enhancement processing to obtain the target thickness image.

[0025] In some embodiments, registering the polar coordinate image in the polar coordinate space to obtain a first deformation vector field in the polar coordinate space includes:

[0026] Scanning the polar coordinate image according to the angle of the polar coordinate space to extract thickness curve information; the thickness curve information is the thickness information corresponding to each of the angles;

[0027] Perform consistency feature extraction according to the thickness curve information to obtain feature points;

[0028] The polar coordinate image is registered in a polar coordinate space according to the feature points to generate the first deformation vector field.

[0029] To achieve the above-mentioned purpose, the second aspect of the present disclosure proposes a retinal image registration device between subjects, comprising:

[0030] An original image acquisition module, used to acquire at least two original images; the original images are images of different subjects, and the original images include optical coherence tomography images of retinal en-face perspectives; the original images include a source image and a target image;

[0031] A retinal thickness calculation module, used to perform retinal thickness calculation processing on the original image to obtain a target thickness image; the target thickness image contains the retinal thickness information in the original image;

[0032] A polar coordinate space transformation module, used for performing polar coordinate space transformation processing on the target thickness image to obtain a polar coordinate image in a polar coordinate space;

[0033] The registration module is used to register the polar coordinate image in the polar coordinate space to obtain the target image in the original image space.

[0034] To achieve the above objective, a third aspect of the present disclosure provides an electronic device, including:

[0035] at least one memory;

[0036] at least one processor;

[0037] at least one program;

[0038] The program is stored in a memory, and the processor executes at least one program to implement the method of the present disclosure as described in the first aspect above.

[0039] To achieve the above objective, a fourth aspect of the present disclosure provides a storage medium, which is a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute:

[0040] As the method according to the first aspect above.

[0041] The inter-subject retinal image registration method and device, electronic device, and storage medium proposed in the embodiments of the present disclosure first acquire at least two original images, then perform retinal thickness calculation processing on the original images to obtain a target thickness image, and then the target thickness image contains the retinal thickness information in the original images, and performs polar coordinate space transformation processing on the target thickness image to obtain a polar coordinate image in the polar coordinate space, and finally registers the polar coordinate images in the polar coordinate space to obtain the target image in the original image space. The technical solution provided in the embodiments of the present disclosure can realize the registration of retinal images for different subjects. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of the inter-subject retinal image registration method provided in the embodiment of the present disclosure.

[0043] Figure 2 yes Figure 1 Flowchart of step S140 in .

[0044] Figure 3 yes Figure 1 A flowchart of step S140 is provided in another embodiment.

[0045] Figure 4 yes Figure 1 Flowchart of step S120 in .

[0046] Figure 5 yes Figure 4 Flowchart of step S430 in .

[0047] Figure 6 yes Figure 3 Flowchart of step S310 in .

[0048] Figure 7 It is a module block diagram of the inter-subject retinal image registration device provided in an embodiment of the present disclosure.

[0049] Figure 8 It is a schematic diagram of the hardware structure of the electronic device provided by the embodiment of the present disclosure.

[0050] Reference numerals: original image acquisition module 710 , retinal thickness calculation module 720 , polar coordinate space transformation module 730 , registration module 740 , processor 801 , memory 802 , input / output interface 803 , communication interface 804 , bus 805 . DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0054] In the field of medical image processing, OCT images are an important means of observing the retina. OCT images can finely present the layered structure of the retina and analyze the morphology and thickness of each layer of the retina. En-face OCT images are projections of three-dimensional OCT images in the en-face direction. Compared with b-scan images and en-face OCT images, they can better present the distribution of the fovea, macula, optic cup and optic disc in the fundus. Therefore, en-face OCT images are often used for retinal area division and feature extraction. In addition, en-face OCT images can also reflect the distribution of fundus blood vessels, which are often used as important features for the registration of OCT images with other modal images such as fundus color photography. Therefore, en-face OCT images play an important role in ophthalmic image analysis.

[0055] The registration of en-face OCT images currently focuses on the registration between en-face OCT images and other modal images (such as fundus color photographs). This registration problem mainly involves the registration between different modalities of ophthalmic images of the same subject, which is used to correct the deformation between different modalities of ophthalmic images in order to fuse multimodal information. However, there is still a lack of relevant methods for the registration of en-face OCT images between different subjects.

[0056] Inter-subject registration of en-face OCT images is mainly used to correct the distribution differences of various retinal areas caused by individual differences, thereby improving the accuracy and convenience of retinal partitioning and feature extraction. It has important practical application value, where "subject" refers to the participants in the experiment or test, and "inter-subject" refers to the registration between images of different experimental participants.

[0057] In medical image registration technology, current registration methods include: regional grayscale-based registration method and feature-based registration method. Among them, the regional grayscale-based registration method extracts the grayscale information (such as histogram information) in the region and uses correlation and mutual information as the objective function for registration; the feature-based registration method achieves registration by finding feature matching points. In the process of OCT (Optical Coherence Tomography) image registration of the retinal en-face perspective within the subject, a feature-based method is usually used to use retinal vascular features for registration.

[0058] The grayscale features in the regional grayscale-based registration method are easily disturbed by the speckle noise on the OCT image, resulting in poor registration effect. Although the feature-based registration method can clearly present the retinal vascular features and find matching feature points through the retinal en-face OCT image, the retinal vascular features have strong individual specificity. The retinal blood vessels of different subjects have great differences in topological structure, vascular morphology and quantity. Therefore, the current image registration method cannot perform registration for retinal images of different subjects.

[0059] Based on this, the embodiments of the present disclosure provide a method and device, an electronic device, and a storage medium for retinal image registration between subjects. At least two original images are first acquired, and then the original images are processed for retinal thickness calculation to obtain a target thickness image. The target thickness image then contains the retinal thickness information in the original images. The target thickness image is transformed into a polar coordinate space to obtain a polar coordinate image in a polar coordinate space. Finally, the polar coordinate images are registered in the polar coordinate space to obtain a target image in the original image space. The technical solution provided by the embodiments of the present disclosure can realize the registration of retinal images for different subjects.

[0060] The current intra-subject registration of en-face OCT images mainly adopts a feature-based method and selects the retinal vascular features for registration. However, different subjects have different retinal vascular distributions, and it is difficult to use vascular features for inter-subject registration. The present application proposes an inter-subject retinal image registration method. Compared with retinal vascular features, the consistency of retinal thickness information between subjects is stronger. Applying retinal thickness information to the registration process can achieve more robust and accurate inter-subject registration.

[0061] In addition, considering the characteristic that retinal thickness is distributed with the macula as the center, the present application proposes a method for retinal image registration between subjects, which is performed in polar coordinate space. Compared with the registration in the original image space, the polar coordinate space is easier to handle features with similar central distribution, thereby improving the accuracy of the registration.

[0062] The embodiments of the present disclosure provide a method and device for retinal image registration between subjects, an electronic device, and a storage medium, which are specifically described through the following embodiments. First, the method for retinal image registration between subjects in the embodiments of the present disclosure is described.

[0063] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0064] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0065] The inter-subject retinal image registration method provided in the embodiments of the present disclosure relates to the field of artificial intelligence technology, and in particular to the field of medical image registration technology. The inter-subject retinal image registration method provided in the embodiments of the present disclosure can be applied to a terminal, or to a server, or can be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, or a smart watch, etc.; the server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms; the software can be an application that implements the inter-subject retinal image registration method, etc., but is not limited to the above forms.

[0066] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0067] The disclosed embodiment proposes a method for retinal image registration between subjects, including: acquiring at least two original images; the original images are images of different subjects, and the original images include optical coherence tomography images of the retina en-face perspective; the original images include a source image and a target image; performing retinal thickness calculation processing on the original images to obtain a target thickness image; the target thickness image contains the thickness information of the retina in the original images; performing polar coordinate space transformation processing on the target thickness image to obtain a polar coordinate image in the polar coordinate space; and registering the polar coordinate images in the polar coordinate space to obtain a destination image in the original image space.

[0068] In some embodiments, registering the polar coordinate images in the polar coordinate space to obtain the target image in the original image space includes:

[0069] Registering the polar coordinate images in the polar coordinate space to obtain a target sub-image in the polar coordinate space;

[0070] The target sub-image is transformed in the original image space to obtain the target image in the original image space.

[0071] Figure 1 is an optional flow chart of the inter-subject retinal image registration method provided in the embodiment of the present disclosure. Figure 1 The method may include but is not limited to steps S110 to S140, specifically including:

[0072] S110, acquiring at least two original images;

[0073] S120, performing retinal thickness calculation processing on the original image to obtain a target thickness image;

[0074] S130, performing polar coordinate space transformation processing on the target thickness image to obtain a polar coordinate image in the polar coordinate space;

[0075] S140, registering the polar coordinate image in the polar coordinate space to obtain a target image in the original image space.

[0076] In step S110, the original images are images of different subjects, where "subjects" refer to participants in experiments or tests, that is, the application scenario targeted by this application is the registration of images of different subjects; the original images include optical coherence tomography images of retinal en-face perspectives, that is, en-face OCT images; the original images include source images and target images, where the number of original images is at least two, where the source image and the target image are images to be registered. Generally speaking, in image registration, the target image is registered to the source image to achieve registration.

[0077] In step S120, the target thickness image contains the thickness information of the retina in the original image. The thickness information is used to introduce the thickness features in the retinal image into the registration process. Compared with the vascular features in the traditional method, the vascular features between different subjects are more different, while the thickness features between different subjects are more consistent, which is conducive to image registration between subjects.

[0078] In step S130 to step S140, the thickness information of the retina has the characteristic of being distributed with the macula as the center, and therefore the target thickness image is transformed into a polar coordinate space, and image registration is first performed in the polar coordinate space. Compared with the method of directly registering in the original image space, the polar coordinate space registration is more suitable for the target thickness image with the characteristic of being distributed with the macula as the center, thereby improving the accuracy of the registration.

[0079] It should be noted that in step S140, the registration method to obtain the target image in the original image space includes but is not limited to two methods: (1) transforming the target thickness image into the polar coordinate space to obtain the target sub-image, then registering the target sub-image, and directly transforming the image obtained after the registration into the original image space to obtain the target image; (2) first transforming the target thickness image into the polar coordinate space to obtain the polar coordinate image, then performing image registration in the polar coordinate space to obtain the deformation vector field, then transforming the deformation vector field back to the original image space, and then using the transformed deformation vector field for registration to obtain the target image.

[0080] Among them, in comparison, the advantage of method (1) is that the image registered in polar coordinate space is directly transformed to the original image space, which improves the efficiency of image registration, while the advantage of method (2) is that the deformation vector field transformed back to the original image space is used to perform registration in the original image space, which reduces the registration error and improves the accuracy of image registration. Method (1) and method (2) can select a more suitable method according to the actual application scenario.

[0081] The inter-subject retinal image registration method proposed in the embodiment of the present disclosure first obtains at least two original images, then performs retinal thickness calculation processing on the original images to obtain a target thickness image, and then the target thickness image contains the retinal thickness information in the original images, and performs polar coordinate space transformation processing on the target thickness image to obtain a polar coordinate image in the polar coordinate space, and finally registers the polar coordinate images in the polar coordinate space to obtain the target image in the original image space. The technical solution provided in the embodiment of the present disclosure can realize the registration of retinal images for different subjects.

[0082] In some embodiments, polar coordinate images are registered in polar coordinate space to obtain a target image in the original image space, including: registering polar coordinate images in polar coordinate space to obtain a target sub-image in the polar coordinate space; and performing original image space transformation processing on the target sub-image to obtain the target image in the original image space.

[0083] Figure 2 is a flowchart of step S140 in some embodiments, Figure 2 The illustrated step S140 includes but is not limited to steps S210 to S220:

[0084] S210, registering the polar coordinate image in the polar coordinate space to obtain a target sub-image in the polar coordinate space;

[0085] S220, performing original image space transformation processing on the target sub-image to obtain the target image in the original image space.

[0086] In step S210, the polar coordinate image is registered in the polar coordinate space to obtain a target sub-image, wherein the polar coordinate image is transformed from the target thickness image, and the target thickness image includes the source image and the target thickness image corresponding to the target image, therefore, the polar coordinate image also includes the polar coordinate images corresponding to the source image and the target image, and the polar coordinate images corresponding to the source image and the target image are the objects of registration in step S210.

[0087] In step S210, the target sub-image obtained is an intermediate product of this method, and the target sub-image is an image that has completed registration in the polar coordinate space.

[0088] In step S220, the target sub-image obtained by registration is transformed back to the original image space to obtain a target image, which is an image in the original image space after registration.

[0089] In some embodiments, registering the polar coordinate images in the polar coordinate space to obtain the destination image in the original image space also includes: registering the polar coordinate images in the polar coordinate space to obtain a first deformation vector field in the polar coordinate space; performing original image space transformation processing on the first deformation vector field to obtain a second deformation vector field in the original image space; and registering the original image according to the second deformation vector field to obtain the destination image.

[0090] Figure 3 is a flowchart of step S140 in some other embodiments, Figure 3 The illustrated step S140 includes but is not limited to steps S310 to S330:

[0091] S310, registering the polar coordinate image in the polar coordinate space to obtain a first deformation vector field in the polar coordinate space;

[0092] S320, performing original image space transformation processing on the first deformation vector field to obtain a second deformation vector field in the original image space;

[0093] S330, registering the original image according to the second deformation vector field to obtain a target image.

[0094] In step S310, the first deformation vector field is a deformation vector field when polar coordinates are used for registration, and represents the image registration process in the polar coordinate space.

[0095] In step S320, the second deformation vector field is the result of the first deformation vector field being transformed into the original image space. It should be noted that the objects of the polar coordinate space transformation processing and the original image space transformation processing can be either images or deformation vector fields, and the processing methods and principles are similar.

[0096] In step S330, the second deformation vector field is used to guide the image registration work in the original image space.

[0097] In some embodiments, the original image is processed for retinal thickness calculation to obtain a target thickness image, including: performing retinal segmentation on the original image to obtain a retinal image; performing thickness calculation on the retinal image to obtain an initial thickness image; and performing image preprocessing on the initial thickness image to obtain a target thickness image.

[0098] Figure 4 is a flowchart of step S120 in some embodiments, Figure 4The illustrated step S120 includes but is not limited to steps S410 to S430:

[0099] S410, performing retinal segmentation on the original image to obtain a retinal image;

[0100] S420, calculating the thickness of the retinal image to obtain an initial thickness image;

[0101] S430, performing image preprocessing on the initial thickness image to obtain a target thickness image.

[0102] In step S410, the retinal area is segmented from the original image to obtain a retinal image for thickness calculation.

[0103] In step S420, the overall retinal thickness is calculated to generate an initial thickness image. Specifically, the initial thickness image is a retinal thickness en-face image.

[0104] In step S430, the generated initial thickness image is subjected to image preprocessing, and the image preprocessing includes but is not limited to image denoising and image enhancement, so as to obtain a processed target thickness image, which is used in a subsequent coordinate transformation process.

[0105] In some embodiments, performing image preprocessing on the initial thickness image to obtain the target thickness image includes: performing image denoising on the initial thickness image to obtain the target thickness image. In some embodiments, performing image preprocessing on the initial thickness image to obtain the target thickness image also includes: performing image enhancement on the initial thickness image to obtain the target thickness image.

[0106] Figure 5 is a flowchart of step S430 in some embodiments, Figure 5 The illustrated step S430 includes but is not limited to steps S510 to S520:

[0107] S510, performing image denoising processing on the initial thickness image to obtain a target sub-thickness image;

[0108] S520, performing image enhancement processing on the target sub-thickness image to obtain a target thickness image.

[0109] In step S510, the target sub-thickness image is an image after image denoising processing has been completed, wherein the image denoising processing includes but is not limited to mean filter denoising, adaptive Wiener filter denoising, median filter denoising, wavelet denoising and the like; in step S520, the target thickness image is an image after image enhancement processing has been completed, wherein the image enhancement processing includes but is not limited to image geometric transformation, color transformation and the like.

[0110] It should be noted that Figure 5 The image denoising process shown is performed before the image enhancement process. Figure 5 The order of image processing shown is only for illustration, representing a means of image preprocessing of the present application, and cannot be understood as limiting the technical solution of the present application. Specifically, the image preprocessing in the present application can be image denoising alone, image enhancement alone, or the two means can be combined in a certain order to facilitate the subsequent image registration work.

[0111] In some embodiments, the polar coordinate image is registered in the polar coordinate space to obtain a first deformation vector field in the polar coordinate space, including: scanning the polar coordinate image according to the angle of the polar coordinate space to extract thickness curve information; the thickness curve information is thickness information corresponding to each angle; consistent feature extraction is performed based on the thickness curve information to obtain feature points; and the polar coordinate image is registered in the polar coordinate space based on the feature points to generate a first deformation vector field.

[0112] Figure 6 is a flowchart of step S310 in some embodiments, Figure 6 The illustrated step S310 includes but is not limited to steps S610 to S630:

[0113] S610, scanning the polar coordinate image according to the angle of the polar coordinate space to extract thickness curve information;

[0114] S620, extracting consistent features according to the thickness curve information to obtain feature points;

[0115] S630: register the polar coordinate image in the polar coordinate space according to the feature points to generate a first deformation vector field.

[0116] In step S610, the polar coordinate image is scanned along the angle dimension of the polar coordinate space to extract thickness curve information corresponding to each angle, wherein the thickness curve information is thickness information corresponding to each angle.

[0117] In step S620, consistent feature points are further extracted from the extracted thickness curve information, where consistency represents consistent thickness features between source images and target images of different subjects.

[0118] In step S630, based on the feature points, the polar coordinate image is registered in the polar coordinate space to generate a first deformation vector field.

[0119] The disclosed embodiment proposes a retinal image registration device between subjects, including: an original image acquisition module, used to acquire at least two original images; the original images are images of different subjects, and the original images include optical coherence tomography images of retinal en-face perspectives; the original images include source images and target images; a retinal thickness calculation module, used to perform retinal thickness calculation processing on the original images to obtain a target thickness image; the target thickness image contains the thickness information of the retina in the original images; a polar coordinate space transformation module, used to perform polar coordinate space transformation processing on the target thickness image to obtain a polar coordinate image in the polar coordinate space; and a registration module, used to register the polar coordinate images in the polar coordinate space to obtain a target image in the original image space.

[0120] See also Figure 7 , Figure 7 An embodiment of an inter-subject retinal image registration device is illustrated, and the inter-subject retinal image registration device includes: an original image acquisition module 710, a retinal thickness calculation module 720, a polar coordinate space transformation module 730, and a registration module 740, wherein the original image acquisition module 710 is connected to the retinal thickness calculation module 720, the retinal thickness calculation module 720 is connected to the polar coordinate space transformation module 730, and the polar coordinate space transformation module 730 is connected to the registration module 740.

[0121] The specific implementation of the inter-subject retinal image registration device of this embodiment is basically consistent with the specific implementation of the above-mentioned inter-subject retinal image registration method, and belongs to the same inventive concept, and will not be repeated here.

[0122] The present disclosure also provides an electronic device, including:

[0123] at least one memory;

[0124] at least one processor;

[0125] at least one program;

[0126] The program is stored in the memory, and the processor executes the at least one program to implement the above-mentioned inter-subject retinal image registration method implemented in the present disclosure. The electronic device can be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a car computer, etc.

[0127] See also Figure 8 , Figure 8 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0128] The processor 801 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present disclosure;

[0129] The memory 802 can be implemented in the form of ROM (Read Only Memory), static storage device, dynamic storage device or RAM (Random Access Memory). The memory 802 can store operating systems and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 802, and the processor 801 is used to call and execute the inter-subject retinal image registration method of the embodiment of the present disclosure;

[0130] Input / output interface 803, used to implement information input and output;

[0131] Communication interface 804, used to realize communication interaction between the device and other devices, which can be realized by wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.); and

[0132] A bus 805 that transmits information between the various components of the device (e.g., the processor 801, the memory 802, the input / output interface 803, and the communication interface 804);

[0133] The processor 801 , the memory 802 , the input / output interface 803 and the communication interface 804 are connected to each other in communication within the device via a bus 805 .

[0134] The embodiment of the present disclosure further provides a storage medium, which is a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned inter-subject retinal image registration method.

[0135] The inter-subject retinal image registration method and device, electronic device, and storage medium proposed in the embodiments of the present disclosure first acquire at least two original images, then perform retinal thickness calculation processing on the original images to obtain a target thickness image, and then the target thickness image contains the retinal thickness information in the original images, and perform polar coordinate space transformation processing on the target thickness image to obtain a polar coordinate image in the polar coordinate space, and finally register the polar coordinate images in the polar coordinate space to obtain the target image in the original image space. The technical solution provided in the embodiments of the present disclosure is used to achieve registration of retinal images for different subjects.

[0136] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0137] The embodiments described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems.

[0138] It can be understood by those skilled in the art that Figure 1-6 The technical solutions shown in the figure do not constitute a limitation on the embodiments of the present disclosure, and may include more or fewer steps than those shown in the figure, or a combination of certain steps, or different steps.

[0139] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0140] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0141] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0142] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0143] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0144] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0145] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0146] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0147] The preferred embodiments of the present disclosure are described above with reference to the accompanying drawings, but the scope of the rights of the present disclosure is not limited thereto. Any modification, equivalent substitution and improvement made by those skilled in the art without departing from the scope and essence of the present disclosure should be within the scope of the rights of the present disclosure.

Claims

1. A method for retinal image registration between subjects, characterized in that: include: Acquire at least two original images; the original images are images of different subjects, and the original images include optical coherence tomography images of retinal en-face perspective; the original images include a source image and a target image; Performing retinal thickness calculation processing on the original image to obtain a target thickness image; the target thickness image contains retinal thickness information in the original image; Performing polar coordinate space transformation processing on the target thickness image to obtain a polar coordinate image in the polar coordinate space; Registering the polar coordinate image in the polar coordinate space to obtain a target image in the original image space; Wherein, registering the polar coordinate image in the polar coordinate space to obtain the target image in the original image space includes: Registering the polar coordinate image in the polar coordinate space to obtain a target sub-image in the polar coordinate space; Performing original image space transformation processing on the target sub-image to obtain the target image in the original image space; The registering the polar coordinate images in the polar coordinate space to obtain the target image in the original image space also includes: Registering the polar coordinate image in the polar coordinate space to obtain a first deformation vector field in the polar coordinate space; Performing original image space transformation processing on the first deformation vector field to obtain a second deformation vector field in the original image space; Registering the original image according to the second deformation vector field to obtain the target image; The registering the polar coordinate image in the polar coordinate space to obtain a first deformation vector field in the polar coordinate space includes: Scanning the polar coordinate image according to the angle of the polar coordinate space to extract thickness curve information; the thickness curve information is the thickness information corresponding to each of the angles; Perform consistency feature extraction according to the thickness curve information to obtain feature points; The polar coordinate image is registered in a polar coordinate space according to the feature points to generate the first deformation vector field.

2. The method according to claim 1, characterized in that The step of performing retinal thickness calculation processing on the original image to obtain a target thickness image includes: Performing retinal segmentation on the original image to obtain a retinal image; Calculating the thickness of the retinal image to obtain an initial thickness image; The initial thickness image is subjected to image preprocessing to obtain the target thickness image.

3. The method according to claim 2, characterized in that The performing image preprocessing on the initial thickness image to obtain the target thickness image includes: The initial thickness image is subjected to image denoising to obtain the target thickness image.

4. The method according to claim 2, characterized in that: The performing image preprocessing on the initial thickness image to obtain the target thickness image further includes: The initial thickness image is subjected to image enhancement processing to obtain the target thickness image.

5. A device for retinal image registration between subjects, characterized in that: include: An original image acquisition module, used to acquire at least two original images; the original images are images of different subjects, and the original images include optical coherence tomography images of retinal en-face perspectives; the original images include a source image and a target image; A retinal thickness calculation module, used for performing retinal thickness calculation processing on the original image to obtain a target thickness image; the target thickness image contains the retinal thickness information in the original image; A polar coordinate space transformation module, used for performing polar coordinate space transformation processing on the target thickness image to obtain a polar coordinate image in a polar coordinate space; A registration module is used to register the polar coordinate image in the polar coordinate space to obtain the target image in the original image space. The registration module is used to register the polar coordinate image in the polar coordinate space to obtain the target image in the original image space, including: Registering the polar coordinate image in the polar coordinate space to obtain a target sub-image in the polar coordinate space; Performing original image space transformation processing on the target sub-image to obtain the target image in the original image space; The registration module is used to register the polar coordinate image in the polar coordinate space to obtain the target image in the original image space, and further includes: Registering the polar coordinate image in the polar coordinate space to obtain a first deformation vector field in the polar coordinate space; Performing original image space transformation processing on the first deformation vector field to obtain a second deformation vector field in the original image space; Registering the original image according to the second deformation vector field to obtain the target image; The registering the polar coordinate image in the polar coordinate space to obtain a first deformation vector field in the polar coordinate space includes: Scanning the polar coordinate image according to the angle of the polar coordinate space to extract thickness curve information; the thickness curve information is the thickness information corresponding to each of the angles; Perform consistency feature extraction according to the thickness curve information to obtain feature points; The polar coordinate image is registered in a polar coordinate space according to the feature points to generate the first deformation vector field.

6. An electronic device, characterized in that: include: at least one memory; at least one processor; at least one program; The program is stored in the memory, and the processor executes at least one of the programs to implement: A method as claimed in any one of claims 1 to 4.

7. A storage medium, the storage medium being a computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a computer to execute: A method as claimed in any one of claims 1 to 4.

Images