A slit lamp ocular segment three-dimensional reconstruction method, system, device and terminal

Abstract

The application belongs to the technical field of three-dimensional reconstruction of the anterior segment system, and discloses a slit lamp anterior segment three-dimensional reconstruction method, system, device and terminal, which comprises the following steps: S1, calculating a plurality of local homography matrices for camera calibration; S2, scanning a series of images of the anterior segment system; S3, performing edge extraction to obtain a pixel point set on the slit lamp projection stripe on the scanned image; S4, performing image region segmentation to further distinguish the cornea, iris, lens and other parts; S5, using the camera calibration parameters to transform the pixel point set on each scanned image to the world coordinates; S6, adjusting the three-dimensional point set corresponding to the cornea, iris, lens and other parts according to the refraction law, and simultaneously performing point cloud gridding to obtain a three-dimensional model of the anterior segment system; the application proposes a method for using a slit lamp to perform three-dimensional reconstruction of the anterior segment system, and overcomes the problems of other methods, such as high cost and inaccurate reconstruction results.

Description

Technical Field

[0001] This invention belongs to the field of three-dimensional reconstruction technology of anterior segment system, and particularly relates to a three-dimensional reconstruction method, system, device and terminal for slit lamp anterior segment. Background Technology

[0002] The incidence of myopia in my country is relatively high, making femtosecond laser treatment for myopia increasingly popular. During femtosecond laser surgery, a thorough understanding of the geometric features of the anterior segment is crucial. Using computer systems to model the three-dimensional structure of the anterior segment (including the cornea, iris, ciliary body, and other tissues) helps doctors gain a comprehensive understanding of relevant information, significantly improving the success rate of the surgery. Currently, there is extensive research on three-dimensional reconstruction of the anterior segment, such as reconstruction methods based on optical coherence tomography (OCT) and slit-lamp microscopy. However, these methods have some limitations. OCT reconstruction methods, based on the principle of light interference, require expensive and sophisticated optical equipment, hindering widespread adoption. Slit-lamp reconstruction methods, on the other hand, require inexpensive equipment that is smaller and easier to use. However, existing slit-lamp reconstruction methods are complex, difficult to implement, and do not consider the imaging parallax caused by the refraction of light by the cornea and lens, thus affecting reconstruction accuracy.

[0003] Based on the above analysis, the problems and shortcomings of existing technologies are as follows: existing reconstruction methods or other solutions based on optical coherence tomography are expensive, hindering widespread adoption. Existing reconstruction methods based on slit-lamp microscopy are theoretically incomplete and do not consider deviations caused by refraction. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention provides a method, system, and device for three-dimensional reconstruction of the anterior segment of a slit lamp.

[0005] This invention is implemented as follows: a method for three-dimensional reconstruction of the anterior segment of a slit lamp, comprising:

[0006] S1, Equipment Calibration: Calculate multiple local homography matrices to calibrate the camera;

[0007] S2, scan a series of images of the anterior segment system;

[0008] S3, perform edge extraction to obtain the set of pixel points at the edge of the slit lamp projection stripes on the scanned image;

[0009] S4 performs image region segmentation to further distinguish the inner and outer surfaces of the cornea, the iris surface, the lens, and other parts;

[0010] S5 uses camera calibration parameters to transform the set of pixels on each scanned image to world coordinates;

[0011] S6. Adjust the three-dimensional point sets corresponding to the cornea, iris, lens and other parts according to the law of refraction, and at the same time perform point cloud meshing to obtain a three-dimensional model of the anterior segment system.

[0012] Furthermore, S1 specifically includes: fixing a calibration plate at the position of the slit lamp light source, aligning the calibration plate with the light plane projected by the slit lamp; then, capturing an image with a camera; detecting and obtaining the corner pixel coordinates of the calibration plate in the image; dividing the entire image into multiple local regions; assigning each corner point to its respective local region; establishing a coordinate system on the slit lamp projection optical plane; calculating the coordinate position of each calibration plate corner point; and combining the pixel coordinates of the corresponding corner points in the image to calculate a homography transformation matrix for each image region. Multiple local transformations are used to overcome the influence of camera lens distortion.

[0013] S2 specifically includes: turning on the slit lamp light source to project an optical section of about 0.5 mm thickness onto the eyeball, moving the scanning device in one direction on the motion track, taking an image of the eyeball at certain distance intervals with the camera, recording the device position corresponding to the image, and obtaining an image sequence after the scanning is completed.

[0014] S3 specifically includes: for each scanned image, firstly, the image is binarized, then an edge detection algorithm is used to obtain the bright spot stripe edges formed by the slit lamp projection plane on the image, and then isolated pixels are removed and the image edges are connected to form a complete set of edge pixels of the anterior segment system.

[0015] S4 specifically includes: using computer vision or deep learning methods, such as the UNET network, to segment the edge image obtained in the previous step, distinguishing the parts of the pixel set that belong to the anterior and posterior surfaces of the cornea, the iris, and the lens, and assigning a label to each point set to determine the specific part of the anterior segment system represented by that point.

[0016] S5 specifically includes: based on each scanned image, the pixel set obtained in S4, and based on the specific pixel coordinates of each pixel, determining the local image region divided in S1, using the homography transformation matrix of this region, transforming the image to coordinates on the slit lamp optical plane, and combining it with the position of the device on the motion track recorded in S2 when scanning the image to form three-dimensional coordinates.

[0017] S6 is a crucial step in the 3D reconstruction of the anterior segment system. The imaging process involves light emitted from a slit lamp, reflected and refracted by various parts of the eye, and finally entering the camera lens to form an image. The refraction effect of light by eye tissue can cause deviations in the reconstruction results. To correct this deviation, this invention proposes a layered reconstruction method. Specifically, firstly, based on the region segmentation markers in S4, the portion of the corneal outer surface in the point cloud in S5 is extracted. A point cloud meshing algorithm is then used to reconstruct the mesh of the corneal outer surface. Next, the normals of the corneal outer surface mesh are calculated and smoothed before being used in the next step. The pixels on the corneal outer surface corresponding to the image are formed by light emitted from the slit lamp, reflected from the corneal outer surface to the camera, without light refraction, resulting in an accurate reconstruction. Next, considering the inner surface of the cornea, direct reconstruction would introduce bias due to the refraction of light rays reaching it by the outer surface. Therefore, when reconstructing the inner corneal surface, the point cloud positions are readjusted based on the obtained outer corneal mesh and normal, and given that the corneal refractive index is approximately 1.376, according to the law of refraction. This corrects the bias, and the corrected point cloud is then reconstructed to obtain the mesh for the inner corneal surface. Subsequently, the same method is used to process and reconstruct deeper ocular tissue surfaces sequentially.

[0018] Another object of the present invention is to provide a slit lamp anterior segment 3D reconstruction system using the aforementioned slit lamp anterior segment 3D reconstruction method, comprising:

[0019] Equipment calibration module: used to calculate multiple local homography matrices for camera calibration;

[0020] Image scanning module, used to scan a series of images of the object to be tested;

[0021] The edge extraction module is used to extract edges and obtain the set of pixels on the slit lamp projection stripes in the scanned image;

[0022] The image segmentation module is used to distinguish the pixel sets of different parts of the anterior segment system;

[0023] The coordinate transformation module is used to generate three-dimensional coordinates by using the calibrated device parameters and the obtained pixel set sequence, and then combining them with the corresponding device position.

[0024] The 3D reconstruction module is used to perform hierarchical reconstruction of point set data to obtain a 3D model of the anterior segment system;

[0025] Another object of the present invention is to provide a computer device including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the slit lamp anterior segment three-dimensional reconstruction method described above.

[0026] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the slit lamp anterior segment three-dimensional reconstruction method.

[0027] Another objective of this invention is to provide an information data processing terminal for implementing the aforementioned three-dimensional reconstruction system for the anterior segment of a slit lamp.

[0028] Based on the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solution to be protected by this invention are as follows:

[0029] First, this invention utilizes a slit-lamp microscope and a single camera, commonly used in ophthalmic examinations, to achieve three-dimensional reconstruction of the anterior segment. Compared to other methods such as optical coherence tomography (OCT), the equipment used in this invention is simpler and less expensive, facilitating widespread adoption. Compared to other slit-lamp-based three-dimensional reconstruction methods for the anterior segment, the equipment calibration and three-dimensional coordinate calculation scheme proposed in this invention are simpler to implement and take into account the influence of camera lens distortion, resulting in speed, efficiency, and accuracy. Furthermore, this invention considers the parallax in camera imaging caused by the refraction effects of light on the inner and outer surfaces of the cornea and the lens. This invention proposes a layered reconstruction method, sequentially reconstructing each ocular tissue surface according to the light transmission path. Using the reconstructed surface model and the refractive index of the corresponding ocular tissue, the three-dimensional coordinate position of the point cloud of the next surface is adjusted to correct the effects of light refraction, making the reconstruction results more accurate.

[0030] This invention employs a simple structure, utilizing a slit-lamp microscope and a single camera for 3D reconstruction. It also addresses the refraction effects of light on eye tissue. The reconstruction equipment proposed in this invention is less expensive and provides more accurate results, making it widely applicable in ophthalmic examinations and femtosecond laser refractive surgery.

[0031] Second, the expected benefits and commercial value of the technical solution of this invention after transformation are as follows:

[0032] Cost savings and equipment availability: Because this invention utilizes simple and low-cost equipment, it is expected to reduce investment costs for ophthalmic examination and eye surgery equipment, enabling more medical institutions and ophthalmologists to purchase and use the system. This will lead to broader market penetration and equipment availability, thereby increasing sales volume and market share.

[0033] Improved accuracy and efficiency: The technical solution proposed in this invention takes into account the refractive effect of eye tissues and corrects parallax caused by light refraction through a layered reconstruction method. It is expected to provide more accurate and efficient three-dimensional reconstruction results of the anterior segment, offering ophthalmologists and ophthalmology professionals more precise information on ocular anatomy, thus helping them make more accurate diagnostic and treatment decisions.

[0034] Application Expansion and Value-Added Services: The technical solution of this invention can be widely applied to ophthalmic examinations and eye surgeries, including femtosecond laser refractive surgery. It is expected to provide value-added services to the ophthalmological medical industry, such as eye disease diagnosis, surgical planning, and surgical outcome evaluation. This will bring more business opportunities and revenue streams to medical institutions and ophthalmologists.

[0035] Competitive Advantages and Differentiation: Compared with traditional anterior segment 3D reconstruction methods such as optical coherence tomography (OCT), the technical solution of this invention has advantages such as simple equipment, low cost, and high accuracy. This will give it a competitive advantage and differentiation in the market, attracting more users to choose and adopt the system, thereby increasing product sales and market share.

[0036] Based on the above factors, the technical solution of this invention is expected to generate significant commercial value and revenue after its commercialization, including increased sales revenue, improved market share, and revenue from value-added services. Specific estimates of commercial value and revenue require further analysis and evaluation based on market research and a business plan.

[0037] Third, the significant technological advancements brought about by this invention:

[0038] 1. By calculating the homography matrix in multiple local image regions for camera calibration, this technique can accurately convert image coordinates into actual physical coordinates, making image processing and 3D reconstruction more precise and improving the diagnostic accuracy of medical images.

[0039] 2. By using the coordinates of the corner points of the calibration plate and combining them with the pixel coordinates of the corresponding corner points on the image, a homography transformation matrix is ​​calculated for each image region. This technological advancement makes the conversion from image coordinates to physical coordinates more accurate, thereby improving the accuracy of 3D reconstruction.

[0040] 3. By using a slit lamp to project an optical cross-section of about 0.5 mm thick onto the eyeball, and moving along a motion track in one direction, the camera can capture an image of the eyeball at certain intervals and record the corresponding device position. This technological advancement makes the scanning process more precise and provides rich source data for subsequent 3D reconstruction.

[0041] 4. By extracting edges, the set of pixel points at the edges of the slit lamp projection stripes on the scanned image is obtained. This technological advancement can extract the main features of the anterior segment system, providing a foundation for subsequent 3D reconstruction and improving the accuracy of 3D reconstruction.

[0042] 5. Using computer vision or deep learning methods, such as the UNET network, for image segmentation, the pixel set can be distinguished as belonging to the anterior and posterior surfaces of the cornea, the iris, and the lens. This technological advancement enables the accurate identification and labeling of various parts of the anterior segment system, improving the accuracy and detail of 3D reconstruction.

[0043] 6. By using camera calibration parameters to transform the set of pixels on each scanned image to world coordinates, this technological advancement provides a conversion from two-dimensional image coordinates to three-dimensional world coordinates, laying a solid foundation for subsequent three-dimensional reconstruction and improving the accuracy of three-dimensional reconstruction.

[0044] 7. Adjusting the coordinates of the cornea, iris, and lens according to the law of refraction takes into account the refraction of light inside the eyeball, making the reconstructed 3D model closer to reality and improving the accuracy and reliability of the 3D model.

[0045] 8. The use of point cloud data for three-dimensional reconstruction of the anterior segment system is a technological advancement that integrates the data acquired and processed in the previous steps to obtain a complete three-dimensional model of the anterior segment system. This enables doctors to make more accurate diagnoses and surgical plans, thereby improving the quality and efficiency of medical services. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a flowchart of the three-dimensional reconstruction method for the anterior segment of a slit lamp provided in an embodiment of the present invention;

[0048] Figure 2 This is a structural diagram of the three-dimensional reconstruction system for the anterior segment of a slit lamp provided in an embodiment of the present invention;

[0049] Figure 3 This is a structural diagram of the calibration platform provided in an embodiment of the present invention;

[0050] Figure 4 This is a schematic diagram of the calibration principle provided in an embodiment of the present invention;

[0051] In the diagram, 1. Eye; 2. Moving platform; 3. Track; 4. Slit lamp light source; 5. Camera; 6. Light plane; 7. Calibration plate. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0053] To address the problems existing in the prior art, the present invention provides a method, system, device, and terminal for three-dimensional reconstruction of the anterior segment of a slit lamp. The present invention will be described in detail below with reference to the accompanying drawings.

[0054] like Figure 1 As shown, the three-dimensional reconstruction method for the anterior segment of a slit lamp provided in this embodiment of the invention includes:

[0055] S1, Equipment Calibration: Calculate multiple local homography matrices to calibrate the camera;

[0056] S2, scan a series of images of the anterior segment system;

[0057] S3, perform edge extraction to obtain the set of pixels on the slit lamp projection stripes in the scanned image;

[0058] S4 performs image region segmentation to further distinguish parts such as the cornea, iris, and lens;

[0059] S5 uses camera calibration parameters to transform the set of pixels on each scanned image to world coordinates;

[0060] S6. Adjust the three-dimensional point sets corresponding to the cornea, iris, lens and other parts according to the law of refraction, and at the same time perform point cloud meshing to obtain a three-dimensional model of the anterior segment system.

[0061] like Figure 2 As shown, the slit lamp anterior segment three-dimensional reconstruction system provided in this embodiment of the invention includes:

[0062] Equipment calibration module: used to calculate the local homography matrix for camera calibration;

[0063] Image scanning module, used to scan a series of images of the object to be tested;

[0064] The edge extraction module is used to extract edges and obtain the set of pixels on the slit lamp projection stripes in the scanned image;

[0065] The image segmentation module is used to distinguish the pixel sets of different parts of the anterior segment system;

[0066] The coordinate transformation module is used to generate three-dimensional coordinates by using the calibrated device parameters and the obtained pixel set sequence, and then combining them with the corresponding device position.

[0067] The 3D reconstruction module is used to perform hierarchical reconstruction of point set data to obtain a 3D model of the anterior segment system;

[0068] like Figure 3 As shown, a slit lamp light source 4 projects a 0.5 mm optical surface onto the eyeball being tested 1. A camera 5 observes the striped bright spots on the eyeball being tested 1 at a 45-degree angle. The relative positions of the slit lamp light source 4 and the camera 5 are fixed. The slit lamp light source 4 and the camera 5 are placed together on the moving platform 2. During reconstruction, the moving platform 2 moves at a constant speed in one direction. The slit lamp light source 4 projects light onto the eyeball being tested 1. The camera 5 takes pictures of the striped bright spots on the eyeball being tested 1 at certain intervals and records the position of the moving platform, forming a scanned image sequence.

[0069] like Figure 4 As shown, the calibration process is as follows: A slit lamp light source 4 projects a 0.5 mm optical plane 6. The checkerboard pattern calibration plate 7 is placed in a position coinciding with the optical plane 6, ensuring that the camera 5 can capture a complete image of the calibration plate 7. The camera 5 captures an image of the calibration plate 7. Following S1, the corner pixel coordinates of the calibration plate in the image are detected, and the image is divided into multiple local regions. The obtained corner pixel coordinates are classified into each local region. A coordinate system is established using the optical plane 6, and the actual coordinates of the corner points of the calibration plate 7 are calculated and matched one-to-one with the corner points in the image. Then, the homography matrix is ​​calculated for each local region.

[0070] An application embodiment of the present invention provides a computer device, which includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of a three-dimensional reconstruction method for the anterior segment of a slit lamp.

[0071] An application embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of a three-dimensional reconstruction method for the anterior segment of a slit lamp.

[0072] An application embodiment of the present invention provides an information data processing terminal, which is used to realize a three-dimensional reconstruction system for the anterior segment of a slit lamp.

[0073] To demonstrate the inventiveness and technical value of the technical solution of this invention, this section provides specific product or related technology application examples of the technical solution claimed.

[0074] Ophthalmic Medical Devices: The technical solution of this invention can be applied to ophthalmic medical devices, such as anterior segment scanners or ocular surgical navigation systems. By employing layered reconstruction methods and light refraction correction techniques, these devices can provide more accurate and refined reconstruction results of ocular anatomy, assisting ophthalmologists in diagnosing eye diseases, planning surgeries, and making treatment decisions.

[0075] Ocular Surgery Assistance System: The technical solution of this invention can be applied to ocular surgery assistance systems, such as femtosecond laser refractive surgery. By combining layered reconstruction methods and light refraction correction technology, this system can provide more accurate ocular structure reconstruction results, helping ophthalmologists with surgical planning and real-time navigation during the procedure, thereby improving the accuracy and safety of the surgery.

[0076] Ophthalmic Diagnostic and Treatment Auxiliary Tools: The technical solution of this invention can also be applied to ophthalmic diagnostic and treatment auxiliary tools, such as ocular disease diagnostic software or ocular image analysis systems. By employing layered reconstruction methods and light refraction correction techniques, these tools can provide more accurate and reliable information on ocular anatomy, assisting ophthalmologists in disease diagnosis, treatment planning, and efficacy evaluation.

[0077] The embodiments of the present invention have achieved some positive results during the research and development or use process, and have indeed great advantages compared with the prior art. The following content describes them in conjunction with the data, charts and other information of the experimental process.

[0078] Through analysis and evaluation of the embodiments of the technical solution of the present invention, the following positive effects are summarized:

[0079] Compared with existing technologies, this invention uses a slit lamp for three-dimensional reconstruction of the anterior segment system, offering the advantage of low cost. The technical solution of this invention uses multiple local homography matrices to calibrate the device, demonstrating higher accuracy and precision in anterior segment three-dimensional reconstruction. Through the slit lamp anterior segment three-dimensional reconstruction method of this invention, the three-dimensional reconstruction of the anterior segment system can be accurately completed. This means that doctors can obtain more realistic and reliable information about the eye structure and make more accurate decisions during diagnosis and surgical planning.

[0080] The technical solution of this invention takes into account the imaging parallax caused by the refraction of light by the cornea and lens, and effectively corrects it. Compared with existing slit-lamp-based reconstruction methods, the reconstruction results of this invention show a significant advantage in reducing parallax errors. This means that the technical solution of this invention can more accurately restore the eye structure and provide more realistic and reliable three-dimensional reconstruction results.

[0081] It should be noted that embodiments of the present invention can be implemented in hardware, software, or a combination of both. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by a suitable instruction execution system, such as a microprocessor or dedicated-design hardware. Those skilled in the art will understand that the above-described devices and methods can be implemented using computer-executable instructions and / or included in processor control code, for example, such code provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The devices and modules of the present invention can be implemented by hardware circuitry such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field-programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of the above-described hardware circuitry and software, such as firmware.

[0082] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions, and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention, and within the spirit and principles of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A slit lamp ocular segment three-dimensional reconstruction method, characterized by comprising: S1, device calibration: calculating a plurality of local homography matrices for camera calibration; S2, scanning a series of images of the ocular segment system; S3, performing edge extraction to obtain a set of slit lamp projected fringe edge pixel points on the scanned images; S4, performing image region segmentation to further distinguish the corneal anterior and posterior surfaces, the iris surface, and the lens part; S5, using the camera calibration parameters to transform the pixel point sets on each scanned image to world coordinates; S6, adjusting the three-dimensional point sets corresponding to the cornea, iris, and lens parts according to the refraction law, and simultaneously performing point cloud gridding to obtain a three-dimensional model of the ocular segment system; S1 specifically comprises: fixing a calibration board at the slit lamp light source position, making the calibration board coincide with the slit lamp projected light plane, and taking an image by the camera to detect and obtain the corner pixel coordinates of the calibration board on the image, dividing the corner points into respective image local regions, calculating the coordinate positions of each calibration board corner point, and calculating a homography transformation matrix for each image region in combination with the pixel coordinates of the corresponding corner points on the image; S2 specifically comprises: turning on the slit lamp light source to project a 0.5 mm thick optical section onto the eyeball, making the scanning device move in one direction on the motion track, and making the camera take an eyeball image at a certain distance interval and record the device position corresponding to the image, to obtain an image sequence after scanning is completed. S3 specifically comprises: obtaining the set of slit lamp projected fringe edge pixel points on the scanned images, performing binarization on each scanned image, using an edge detection algorithm to obtain the bright spot fringe edge formed by the slit lamp projection plane on the image, removing isolated pixel points, and connecting the image edges to form the edge pixel point set of the ocular segment system.

2. The slit lamp ocular segment three-dimensional reconstruction method of claim 1, wherein, S4 specifically comprises: using a UNET network to perform image segmentation to distinguish the parts of the pixel point set belonging to the anterior and posterior surfaces of the cornea, the iris, and the lens, respectively, and assigning a label to each point set to determine the specific part of the ocular segment system represented by the point.

3. The slit lamp ocular segment three-dimensional reconstruction method of claim 1, wherein, S5 specifically comprises: according to each scanned image, determining the local image region divided in the device calibration step from the pixel point set obtained in the S3 step according to the specific pixel coordinates of each pixel point, using the homography transformation matrix of the region to transform the image to the coordinates on the slit lamp optical plane, and combining the position of the device on the motion track when the image is scanned to form a three-dimensional coordinate.

4. The method of claim 1, wherein the method further comprises: S6 comprises adjusting the coordinates of the cornea, iris, and lens according to the refraction law, determining the contact points of the slit lamp light source and the ocular segment system, adjusting the coordinates of the parts according to the refractive index of the ocular segment system using the refraction law, and obtaining the three-dimensional coordinates in the actual space.

5. The method of claim 1, wherein the method further comprises: S6 further comprises using point cloud data to perform three-dimensional reconstruction of the ocular segment system, using Poisson reconstruction to perform three-dimensional reconstruction of the three-dimensional coordinate point cloud data obtained in the S6 step to obtain a three-dimensional model of the ocular segment system, and integrating the obtained and processed data to finally obtain a complete three-dimensional model of the ocular segment system.

6. The slit lamp ocular segment three-dimensional reconstruction method of claim 1, wherein, ​ 7. A slit lamp ocular segment three-dimensional reconstruction system using the slit lamp ocular segment three-dimensional reconstruction method according to any one of claims 1 to 6, characterized by, ​ An apparatus calibration module is configured to calculate a plurality of local homography matrices for camera calibration; An image scanning module is configured to scan a series of images of the anterior segment system; An edge extraction module is configured to perform edge extraction to obtain a set of pixel points on the slit lamp projection stripe in the scanned image; An image segmentation module is configured to distinguish the pixel point sets of each part of the anterior segment system; A coordinate transformation module is configured to form a three-dimensional coordinate by using the calibrated apparatus parameters, the obtained pixel point set sequence, and the corresponding apparatus position; A three-dimensional reconstruction module is configured to perform layered reconstruction on the point set data to obtain a three-dimensional model of the anterior segment system. 8.An information data processing terminal, configured to implement the slit lamp anterior segment three-dimensional reconstruction system of claim 7.

Images