Visual analysis-based navigation system for cataract surgery

Through a navigation system based on visual analysis, image processing technology is used to determine the incision size of cataract surgery, which solves the problem of difficulty in grasping the incision size in the prior art, and improves the safety of the surgery and the speed of vision recovery.

CN119074382AInactive Publication Date: 2024-12-06EYE & ENT HOSPITAL SHANGHAI MEDICAL SCHOOL FUDAN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411214009.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-31
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

It is difficult to grasp the size of the incision in existing cataract surgery, resulting in increased surgical risks and reduced visual recovery speed, especially for novice doctors.

Method used

Using a navigation system based on visual analysis, through image acquisition, image analysis and incision navigation modules, the patient's eye crystal imaging pictures are obtained, grayscale processing, edge outline, triangle mesh formation, Hough transformation matching, determine the incision length and ensure the incision. Size and plan.

Benefits of technology

It improves the accuracy and safety of surgical incision planning, reduces the difficulty of operation for novice doctors, and increases the speed of patients' vision recovery.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119074382A_ABST
    Figure CN119074382A_ABST
Patent Text Reader

Abstract

The invention discloses a visual analysis-based navigation system for cataract surgery in the medical field, and the system comprises an image collection module which is used for obtaining an eye crystal imaging picture of a patient, and carrying out the gray processing of the eye crystal imaging picture; the image analysis module is used for analyzing the eye crystal imaging picture, firstly performing edge outlining on a crystal nucleus lesion region in the eye crystal imaging picture, marking the distribution of turbid regions in the crystal, and connecting each turbid region with the nearest turbid region to form a plurality of triangular grids; extracting an outer side edge line of a closed graph formed by the plurality of triangular meshes, and performing elliptical region matching on the outermost side edge line of the closed graph by using Hough transformation to obtain a crystal nucleus contour line; and the incision navigation module is used for performing center amplification on the crystal nucleus contour line to obtain an operation area, and navigating by taking the long axis of the operation area as the incision length. By the adoption of the technical scheme, the size of the incision can be planned, and operation of a green doctor is facilitated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the medical field, and in particular is a navigation system based on visual analysis for cataract surgery. Background Art

[0002] Cataract is a disease caused by a variety of factors that lead to metabolic disorders of the eye lens. As the disease progresses, it can lead to protein denaturation and turbidity. The clinical manifestations of cataract patients are mainly vision loss and blurred vision. When the turbidity of the lens nucleus reaches brown, it is considered a hard nucleus. This degree of vision loss is obvious and seriously affects the quality of life. Only then will the elderly go to the hospital for surgery. The risk of cataract surgery at this level will also increase accordingly.

[0003] In the prior art, the incision position and the cataract lesion area are identified respectively. In the treatment of hard nuclear cataracts, small incision non-phacoemulsification cataract surgery is often used. Small incision non-phacoemulsification cataract surgery is easy to operate and greatly shortens the operation time. A small incision can help speed up the recovery of vision, but the control of the size of the surgical incision is extremely unfriendly to novice doctors. An incision that is too large increases the trauma area and increases surgical astigmatism, which slows down the patient's recovery rate, while an incision that is too small increases the difficulty of subsequent lens delivery. Summary of the invention

[0004] In order to solve the above problems, the object of the present invention is to provide a navigation system based on visual analysis for cataract surgery, which can plan the incision size.

[0005] In order to achieve the above-mentioned object, the technical solution of the present invention is as follows: A navigation system based on visual analysis for cataract surgery, comprising:

[0006] Image acquisition module: used to obtain the patient's eye lens imaging picture, remove the noise from the eye lens imaging picture and perform grayscale processing;

[0007] Image analysis module: used to analyze the eye lens imaging pictures, first outline the edge of the lens nucleus lesion area in the eye lens imaging pictures, mark the distribution of the turbid area in the lens, connect each turbid area with its nearest turbid area to form a number of triangular grids, extract the outermost edge line of the closed figure formed by the several triangular grids, and then use Hough transform to match the outermost edge line of the closed figure with an elliptical area to obtain the outline of the lens nucleus;

[0008] Incision navigation module: zoom in on the center of the crystal nucleus outline to obtain the operation area, and use the long axis of the operation area as the incision length for navigation.

[0009] The following beneficial effects were achieved by adopting the above scheme: Cataracts are caused by the denaturation of lens proteins and become cloudy, causing patients to have vision loss. The lens is a biconvex transparent tissue that is elastic and is suspended by suspensory ligaments behind the iris and in front of the vitreous. As the cataract worsens, the lens opacity begins to increase in density from the center of the lens, gradually worsens and slowly spreads to the periphery. The opacity will harden, eventually leading to an increase in the hardness of the lens. Depending on the severity of the cataract, the proportion of opacity in the lens is different. Therefore, it is necessary to determine the hardened area based on the distribution of the opacity area in the lens, so as to plan the size of the incision.

[0010] The image acquisition module is used to collect crystal nucleus imaging pictures, remove noise interference, and use grayscale processing to reduce the computing power burden brought by color judgment. Crystal opacity makes the diseased part and the normal part obviously different, so that the edge of the turbid lesion area can be distinguished from the grayscale gradient and the lesion area can be outlined. However, depending on the disease, the turbid area may not completely cover the crystal, and the turbid area may be scattered or irregular. The crystal in the non-lesion area is still elastic and easy to remove, so the incision is planned based on the turbid lesion area. To minimize the length of the incision.

[0011] By connecting each turbid area with its nearest turbid area to form several triangular meshes, a closed figure formed by several triangular meshes is obtained, and the outermost edge line of the closed figure is extracted to obtain the coordinate range containing all turbid areas, and the surgical incision area is planned based on this range.

[0012] Hough transform is a method for detecting regular shapes. One advantage of Hough transform is that it is not affected by noise and curve discontinuity and can effectively detect shapes in images. Hough transform is used to match elliptical regions to obtain elliptical lens nucleus contours that include various turbid regions. Since the lens needs to be delivered and inserted during the operation, the insertion space of the key needs to be expanded. Therefore, the center of the lens nucleus contour is enlarged, and the long axis of the operation area is taken as the incision length.

[0013] Furthermore, Gaussian filtering is used to remove noise in the image acquisition module.

[0014] Beneficial effects: Gaussian filtering is a linear smoothing filter suitable for eliminating Gaussian noise.

[0015] Furthermore, the triangular mesh in the image analysis module is inscribed with the turbid region.

[0016] Beneficial effects: Insection can better determine the boundaries of closed figures and improve planning accuracy.

[0017] Furthermore, in the image analysis module, after a single triangular mesh is generated, the triangular mesh is expanded so that it is additionally connected to a nearest turbid region to form a quadrilateral.

[0018] Beneficial effect: In the process of using triangular meshes to judge the main grayscale area, a large number of triangular areas inside the closed figure are invalid, so the triangle lines are expanded and transformed into quadrilaterals. The quadrilateral can be regarded as the fusion of two triangles. The line segment shared between the two triangles is obviously not the outermost edge line, so it can be directly ignored to reduce the amount of calculation.

[0019] Furthermore, the Sobel operator is used to outline the edge of the crystal nucleus lesion area in the image analysis module.

[0020] Beneficial effects: The Sobel operator uses the gray value difference of the four neighborhoods of each pixel in the image to perform calculations, which can better extract the edge of the crystal nucleus lesion area.

[0021] Furthermore, the magnification of the crystal nucleus outline in the incision navigation module is 1.2 to 1.3.

[0022] Beneficial effect: A magnification of 1.2 to 1.3 can leave a suitable space for delivery operation, making the operation easier.

[0023] Furthermore, it also includes an eye fixation module, which is used to fix the patient's eyeball through a negative pressure suction ring.

[0024] Beneficial effects: The eye fixation module is used to fix the patient's eyes, effectively reducing the deflection of the patient's eyeball during surgery.

[0025] Furthermore, the incision navigation module is applied to manual surgical operation navigation or femtosecond laser planning assistance.

[0026] Beneficial effects: The incision can also be completed automatically by femtosecond laser surgery, but the incision in femtosecond laser surgery still needs to be manually planned, so the incision navigation module can be used to assist in the incision planning of femtosecond laser surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 Schematic diagram of an embodiment of the present invention.

[0028] Figure 2 A schematic diagram of the quadrilateral grid connections.

[0029] Figure 3 A schematic diagram of the operating area. DETAILED DESCRIPTION

[0030] The following is further described in detail through specific implementation methods:

[0031] The reference numerals in the drawings of the specification include: turbid area 1, connecting line 2, closed figure 3, crystal nucleus outline 4, and operation area 5.

[0032] Embodiment 1

[0033] The embodiment is basically as shown in the attached Figure 1 To Attachment Figure 3 As shown:

[0034] A navigation system based on visual analysis for cataract surgery, comprising:

[0035] Eye fixation module: used to fix the patient's eyeball through a negative pressure suction ring;

[0036] Image acquisition module: used to obtain the patient's eye lens imaging picture, perform Gaussian filtering on the eye lens imaging picture to remove noise and then perform grayscale processing;

[0037] Image analysis module: used to analyze the eye lens imaging picture. First, the edge of the lens nucleus lesion area in the eye lens imaging picture is outlined using the Sobel operator. The calculation formula of the Sobel operator is:

[0038] S i =h(i-1,j-1)-h(i-1,j+1)+2h(i,j-1)-2h(i,j+1)+h(i+1,j-1)-h(i+1,j+1)

[0039] S j =h(i-1,j-1)+2h(i-1,j)+h(i-1,j+1)-h(i+1,j-1)-2h(i+1,j)-h(i+1,j+1);

[0040] Among them, h(i,j) is the coordinate point of the image, Si and Sj are the gradients of the image in the horizontal and vertical directions respectively;

[0041] Mark the distribution of the turbid area 1 in the crystal, connect the turbid area 1 with its nearest turbid area 1 by lines 2 to form several triangular meshes, inscribe the triangular meshes with the turbid area 1, expand the triangular meshes so that it is additionally connected to an nearest turbid area 1 to form a quadrilateral, extract the outermost edge line of the closed figure 3 formed by the several quadrilateral meshes, and then use Hough transform to perform elliptical area matching on the outermost edge line of the closed figure 3 to obtain the crystal nucleus contour line 4;

[0042] Incision navigation module: The crystal nucleus contour line 4 is centrally magnified with a magnification of 1.2 to 1.3 times to obtain the operation area 5, and the long axis of the operation area 5 is used as the incision length for navigation. The incision navigation module is used in manual surgical operation navigation or femtosecond laser planning assistance.

[0043] The specific implementation process is as follows: Cataracts are caused by the denaturation of lens protein and become cloudy, causing patients to have vision loss. The lens is a biconvex transparent tissue that is elastic and is suspended by suspensory ligaments behind the iris and in front of the vitreous. As the cataract worsens, the lens opacity begins to increase in density from the center of the lens, gradually worsens and slowly spreads to the periphery. The opacity will harden, eventually leading to an increase in the hardness of the lens. Depending on the severity of the cataract, the proportion of opacity in the lens is different. Therefore, it is necessary to determine the hardened area based on the distribution of the opacity area 1 in the lens, so as to plan the size of the incision.

[0044] The image acquisition module is used to collect crystal imaging pictures, use Gaussian filtering to remove noise interference, and use grayscale processing to reduce the computing power burden brought by color judgment. Crystal opacity makes the diseased part and the normal part have obvious differences, so that the edge of the turbid lesion area can be distinguished from the grayscale gradient and the lesion area can be outlined. The Sobel operator is used. The Sobel operator uses the grayscale value difference of the four neighborhoods of each pixel in the image to perform calculations, which can better extract the edge of the crystal nucleus lesion area. However, depending on the symptoms, the turbid area 1 may not completely cover the crystal, and the turbid area 1 may be scattered or irregular. The crystal in the non-lesion area still retains elasticity and is easy to remove, so the incision is planned based on the turbid lesion area to minimize the length of the incision.

[0045] By connecting each turbid area 1 with its nearest turbid area 1 to form several triangular meshes, a closed figure 3 formed by several triangular meshes is obtained, and the outermost edge line of the closed figure 3 is extracted to obtain the coordinate range containing all turbid areas 1. In the process of using triangular meshes to judge the main grayscale area, a large number of triangular areas inside the closed figure 3 are invalid, so the triangular connection 2 is expanded and converted into a quadrilateral. The quadrilateral can be regarded as the fusion of two triangles. The line segment shared between the two triangles is obviously not the outermost edge line, so it can be directly ignored to reduce the amount of calculation. The surgical incision area is planned based on this range.

[0046] Hough transform is a method for detecting regular shapes. One advantage of Hough transform is that it is not affected by noise and curve discontinuity and can effectively detect shapes in images. Hough transform is based on the voting algorithm in statistics. It estimates the position of regular graphics in the image space by counting the maximum points in the parameter space, thereby matching the elliptical area and obtaining the elliptical crystal nucleus contour line 4 containing each turbid area 1. Since the crystal needs to be delivered and inserted during the operation, the exploration space of the key needs to be expanded. Therefore, the center of the crystal nucleus contour line 4 is enlarged, and the long axis of the operation area 5 is taken as the incision length.

[0047] Users can perform surgical operations based on navigation, thereby planning a more appropriate incision size to facilitate subsequent delivery and implantation operations and enable patients to recover faster, reducing the difficulty of surgical operations for novice doctors.

[0048] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A navigation system based on visual analysis for cataract surgery, characterized in that: include: Image acquisition module: used to obtain the patient's eye lens imaging picture, remove the noise from the eye lens imaging picture and perform grayscale processing; Image analysis module: used to analyze the eye lens imaging pictures, first outline the edge of the lens nucleus lesion area in the eye lens imaging pictures, mark the distribution of the turbid area in the lens, connect each turbid area with its nearest turbid area to form a number of triangular grids, extract the outermost edge line of the closed figure formed by the several triangular grids, and then use Hough transform to match the outermost edge line of the closed figure with an elliptical area to obtain the outline of the lens nucleus; Incision navigation module: zoom in on the center of the crystal nucleus outline to obtain the operation area, and use the long axis of the operation area as the incision length for navigation.

2. The navigation system based on visual analysis for cataract surgery according to claim 1, characterized in that: Gaussian filtering is used to remove noise in the image acquisition module.

3. The navigation system based on visual analysis for cataract surgery according to claim 2, characterized in that: The triangular mesh is inscribed with the turbidity region in the image analysis module.

4. The navigation system based on visual analysis for cataract surgery according to claim 3, characterized in that: In the image analysis module, after a single triangle mesh is generated, the triangle mesh is expanded so that it is additionally connected to a nearest turbid region to form a quadrilateral.

5. The navigation system based on visual analysis for cataract surgery according to claim 4, characterized in that: The Sobel operator is used to outline the edge of the crystal nucleus lesion area in the image analysis module.

6. The navigation system based on visual analysis for cataract surgery according to claim 5, characterized in that: The magnification of the crystal nucleus outline in the incision navigation module is 1.2 to 1.3 times.

7. The navigation system based on visual analysis for cataract surgery according to claim 6, characterized in that: It also includes an eye fixation module, which is used to fix the patient's eyeball through a negative pressure suction ring.

8. The navigation system based on visual analysis for cataract surgery according to claim 7, characterized in that: The incision navigation module is used for manual surgical operation navigation or femtosecond laser planning assistance.