Intelligent assisted phacoemulsification system for phakic intraocular lens

Abstract

The present application relates to a kind of intelligent auxiliary prescription systems of lens eye intraocular lens, comprising: haptics landing line acquisition module, obtain the three-dimensional structure data of anterior chamber and posterior chamber, construct 3D topographic map of ciliary sulcus area by AI three-dimensional image semantics analysis, obtain the best fitting ciliary sulcus line by fitting, with the best fitting ciliary sulcus line as reference, calculate and obtain haptics landing line;Ideal haptics determination module, according to the lateral depth difference between each point on haptics landing line, obtain the ideal haptics position combination sequence of intraocular lens;Crystal matching module, obtain the inventory data of crystal, based on the arch height prediction range and ideal haptics position combination sequence obtained in advance, obtain the best matching intraocular lens and its implant rotation position scheme from the crystal inventory.Compared with prior art, the present application has the advantages of high accuracy of crystal size matching, meeting the stability requirements of crystal implantation, more accurately guiding how to rotate and adjust arch height of crystal and optimizing crystal prescription process.

Description

Technical Field

[0001] This invention relates to the field of phakic eye selection technology, and in particular to an intelligent assisted lens-attaching system for phakic intraocular lenses. Background Technology

[0002] Posterior chamber phakic intraocular lenses (ICLs) have undergone more than 20 years of research and improvement, from V0 to V4c, from a flat "boob tie" to the appearance of foot loops, arch height, and central hole, and even the V5 large optical zone and the V6 presbyopia design. The design of ICL itself has become increasingly perfect, which is why more than 1 million lenses have been implanted worldwide, making ICL implantation the most promising refractive surgery method in the future.

[0003] However, given the complex structure of the eyeball, the limited space of the posterior chamber, and the varied shapes of the ciliary sulci, current ICLs, taking the V4c version as an example, only offer four lengths: 12.1mm, 12.6mm, 13.2mm, and 13.7mm, and are also constrained by the astigmatic axis. Since the internal structures of the human eye vary in size, the appropriate length is typically calculated using a calculator provided by the manufacturer, combined with the doctor's experience. This method has many unpredictable aspects, including unexpected dome height after lens implantation and rotational misalignment due to the inability to fully explore the ciliary sulcus shape.

[0004] Current standard methods for ICL selection in the medical field include UBM (Ultra-Body Measurement) to measure the transverse diameter of the ciliary sulcus at various points (span-to-span distance, STS). Generally, a larger STS allows for the selection of a longer ICL, as the STS for the horizontal diameter is typically shorter than that for the vertical diameter. Therefore, if the STS is too small, the expected arch height after ICL implantation will be higher. In general, the ICL lens can be rotated from the horizontal direction to the vertical direction during surgery to reduce the arch height. However, accurately predicting the STS is currently difficult. This is because the human eye has 70-80 ciliary processes; measurements taken on convex areas of the ciliary process surface will be shorter, while measurements taken on concave areas will be longer, introducing uncertainty. Even when measurements are taken on concave areas, besides measurement errors, it is impossible to definitively confirm whether the four haptics of the ICL fall on concave or convex areas, leaving further uncertainty.

[0005] Existing patent TW202123892A discloses a method for determining the rotation of ICL dimensions, but it only finds correlations among 2D parameters and has the shortcoming of not being accurate enough in predicting the final landing position of the loop.

[0006] In addition, the landing feet of the ICL in the ciliary sulcus area are inherently unstable. The landing feet can be at various vertical heights above, middle and below the ciliary body, or they can get stuck in the cystic area within the ciliary sulcus, causing unexpected ICL lens displacement, rotation, tilting, etc. In addition to potentially affecting the quality of visual correction, there is also a risk of complications such as glaucoma and cataracts.

[0007] Therefore, how to properly rotate the ICL and how to adjust the rotation angle of the ICL implantation during surgery to ensure that the ICL is in the most stable fixed position inside the eye are technical problems that urgently need to be solved in this field.

[0008] On the other hand, there are limited custom sizes and quantities of astigmatism-correcting ICLs (Toric ICL, TICL) in the manufacturer's lens library. When correcting astigmatism, in order to accurately correspond to the axis of astigmatism correction, the arch height cannot be adjusted by arbitrary rotation during implantation. Therefore, there is also a limitation on the range of implantation rotation angle. As a result, TICL often presents difficulties in ordering lenses, which is also a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0009] The purpose of this invention is to overcome the shortcomings of the prior art and provide an intelligent assisted lens-mounting system for phakic intraocular lenses that has high accuracy in matching lens size and meets the requirements for stable lens implantation.

[0010] The objective of this invention can be achieved through the following technical solutions:

[0011] A smart-assisted lens-attaching system for phakic intraocular lenses includes:

[0012] The loop landing line acquisition module is used to acquire three-dimensional structural data of the anterior and posterior chambers. Based on the three-dimensional structural data, a 3D topographic map of the ciliary sulcus region is constructed through artificial intelligence (AI) image semantic analysis. An imaginary best-fit ciliary sulcus line that fits the actual ciliary sulcus surface is obtained. The loop landing line is calculated using the best-fit ciliary sulcus line as a reference. The coordinates of the points on the loop landing line consist of lateral depth and vertical depth.

[0013] The ideal haptic determination module is used to calculate the lateral depth difference between points on the haptic landing line based on the lateral depth, and simultaneously obtain the ideal haptic position combination sequence of the four haptics of the intraocular lens based on the true STS of the haptic landing line. In this sequence, each ideal haptic position combination corresponds to a stability score, and each ideal haptic position combination is sorted from high to low according to the stability score.

[0014] The lens matching module is used to acquire lens inventory data. Based on the pre-obtained arch height prediction range and the ideal haptic position combination sequence, the module uses a voting matching algorithm to obtain the best-fit intraocular lens and the implantation rotation scheme for adjusting the arch height from the lens inventory. The best-fit intraocular lens preferentially meets the arch height prediction range and has the ideal haptic position combination with a higher stability score.

[0015] Furthermore, in the voting matching algorithm, the most suitable intraocular lens size is determined based on the pre-obtained arch height prediction range and the ideal haptic position combination with the highest stability score in the ideal haptic position combination sequence. Based on the lens inventory data, it is determined whether there is a matching lens inventory. If so, the best-fit intraocular lens and implantation rotation scheme are obtained. If not, a downgrade calculation is performed based on the ideal haptic position combination sequence.

[0016] Furthermore, the 3D topographic map of the ciliary groove region is the area formed by the connection of the surfaces of the posterior chamber structure.

[0017] Furthermore, the central axis of the optimally fitted ciliary sulcus line is parallel to the optical axis, visual axis, or central axis of the eyeball.

[0018] Furthermore, the points on the loop landing line are either points where the probability of loop landing is within a certain probability range or points where the equilibrium probability of landing of the four loops of the intraocular lens is within a certain probability range.

[0019] Furthermore, the points on the landing line of the slack are obtained based on the landing point probability prediction model, which obtains the possible landing probability of the slack at a certain vertical depth.

[0020] Furthermore, the stability of the ideal haptic position combination is obtained by summing the stability of the four haptics of the intraocular lens. The stability is determined based on the lateral depth difference within a set angle on the haptic landing line. The greater the lateral depth difference, the higher the stability.

[0021] Furthermore, the arch height prediction range is obtained based on an AI big data model, the diagonals of the four haptics of the intraocular lens, and a 360° real STS prediction determined by the haptic landing line. Intraocular lenses of different sizes have different arch height prediction ranges.

[0022] Furthermore, the optimally fitted intraocular lens is at least one type.

[0023] Furthermore, the artificial lens includes an ICL lens without astigmatism or an ICL lens with astigmatism.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] 1. This invention explores the global ciliary sulcus morphology based on three-dimensional structural data of the anterior and posterior chambers, and combines AI to reconstruct the posterior chamber model and AI to calculate the most suitable implantation angle, accurately guiding the customization of the rotation angle and ICL length implanted in the eye. The rotation angle can be accurate to 1 degree, better meeting the pre-predicted arch height value.

[0026] 2. This invention enables the optimal rotational position implantation of each ICL (including astigmatism lenses), precise design of the arch height, and prevention of problems such as tilting and rotational misalignment after ICL implantation.

[0027] 3. This invention can automatically match stocked crystals, significantly reducing the clinical ordering process and the error rate of human verification, so as to realize AI-automated ICL ordering. Attached Figure Description

[0028] Figure 1 This is a schematic diagram illustrating the optimal fit of the ciliary sulcus line in this invention;

[0029] Figure 2 This is a schematic diagram of a possible loop contact point of the present invention;

[0030] Figure 3 This is a schematic diagram of the landing line of the present invention;

[0031] Figure 4 This is a schematic diagram illustrating the depth difference calculation of the present invention;

[0032] Figure 5 This is a schematic diagram of the loop of the present invention;

[0033] Figure 6 This is a schematic diagram of the depth difference at different angles according to the present invention;

[0034] Figure 7 The diagram shows two loop rotation schemes obtained in the embodiment, where (7a) is scheme A and (7b) is scheme B;

[0035] Figure 8 This is a schematic diagram of lens implantation;

[0036] Figure 9 This is a schematic diagram of the specific process of the intelligent assisted film ordering system of the present invention;

[0037] Figure 10 This is a schematic diagram of the data closed-loop prediction process of the present invention. Detailed Implementation

[0038] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are implemented based on the technical solution of the present invention, providing detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.

[0039] Example 1

[0040] This embodiment provides an intelligent assisted lens-attaching system for phakic intraocular lenses (IOLs), including a haptic landing line acquisition module, an ideal haptic determination module, and a lens matching module. Based on inventory, this system can accurately provide the appropriate IOL and the most suitable haptic landing angle (i.e., the required implantation rotation angle). This angle ensures the stability of the IOL after implantation and prevents it from easily rotating, providing doctors with automated, intelligent, and effective assistance. The specific operation of each module of this system is described below.

[0041] In the haptic landing line acquisition module, the specific process of acquiring the haptic landing line LL includes:

[0042] Obtain three-dimensional structural data of the anterior and posterior chambers. Based on the three-dimensional structural data, construct a 3D topographic map of the ciliary sulcus region through AI three-dimensional image semantic analysis. Fit an imaginary best-fit ciliary sulcus line that fits the actual ciliary sulcus surface. Using the best-fit ciliary sulcus line as a reference, calculate the loop landing line. The coordinates of the points on the loop landing line consist of lateral depth and vertical depth.

[0043] The three-dimensional anterior chamber and posterior chamber structure data can be acquired using a three-dimensional anterior segment measurement device capable of measuring the posterior chamber structure or a non-contact device. Furthermore, multiple sets of data can be measured using different devices or the same device under different lighting conditions or external ocular physiological stimuli to improve the accuracy of subsequent machine learning (ML) predictions of anterior chamber height. Contact devices for three-dimensional anterior segment measurement can include 3D UBM, while non-contact devices can include Schemimpflug rotational imaging and anterior segment OCT.

[0044] The AI ​​3D image semantics can employ existing algorithms, such as existing 3D image classification, semantic segmentation, and reconstruction algorithms. The training data used is retrieved from an AI database that stores known eye structure data and adapted ICL data.

[0045] After obtaining the morphology of various points on the ciliary sulcus surface, a 3D topographic map of the ciliary sulcus region is constructed. This 3D topographic map represents the area formed by the surface connections of the ciliary body, ciliary sulcus, ciliary sulcus cyst, suspensory ligament, and lens, among other posterior chamber structures. The ciliary sulcus line (LS) is extracted by computer, and an imaginary elliptical annular groove that conforms to the ciliary sulcus surface is further fitted, namely the best-fit line of the ciliary sulcus (BFLS). This is an ideal fitted line with uniform height and depth, such as... Figure 1As shown, this is a three-dimensional virtual line, expressed by the x, y, and z axes of solid geometry. The BFLS (Browser-Fractor System) serves as the reference line for calculating all structural differences. The central axis of the best-fit ciliary sulcus is parallel to the visual axis, optical axis, or central axis of the eyeball to ensure good visual quality and structural stability after BFLS-guided lens implantation.

[0046] Points on the loop landing line are either points where the probability of loop landing falls within a certain probability interval, or points where the equilibrium probability of landing for the four loops of the intraocular lens falls within a certain probability interval. The points on the loop landing line are obtained based on a landing point probability prediction model, which obtains the probability of loop landing at a certain vertical depth.

[0047] The landing point probability prediction model can be an existing probability prediction model, using training data retrieved from the aforementioned AI database. For example... Figure 2 As shown, using BFLS as a relative reference, the height difference (i.e., vertical depth difference) is calculated to obtain the height of the possible loop landing point, and the probabilistic expression of the loop landing site is obtained. The possible probability can be set manually or set to the range of 30% to 90% of the probability of interest according to the software calculation requirements.

[0048] To further illustrate, on the same coronal section, the three-dimensional trajectory map constructed by connecting the possible landing sites of the loop under the aforementioned probability of interest setting, i.e., the landing line (LL), is formed by connecting lines L1, L2, L3..., Ln (for example, 360 to 720 acquisition points). Taking 360 sites as an example, they are labeled as L1 to Ln. 360 The difference between L1 and L2 is 1°, and each L... n Each has its own coordinate data, with BFLS as the relative coordinate origin for reference, such as Figure 3 As shown. LL and LS differ. Sometimes the loop doesn't land on LS first, but on LL. LL can span the upper, middle, or lower part of the ciliary body, or a specific point on the surface of the wide ciliary sulcus. LL is calculated based on its position on the posterior surface of the iris and large datasets. Example coordinates of LL: L1(H8, D4), where H is the height scale, also known as vertical depth, and D is the depth value, also known as lateral depth.

[0049] In the ideal haptic lug determination module, the depth difference between points on the haptic lug landing line is calculated based on the lateral depth. Simultaneously, based on the true STS (Surface Time Tolerance) of the haptic lug landing line, a sequence of ideal haptic lug position combinations for the four haptic lugs of the intraocular lens is obtained. Each ideal haptic lug position combination in this sequence corresponds to a stability score, and the ideal haptic lug position combinations are sorted from highest to lowest based on these stability scores. This ideal haptic lug determination module can calculate the most suitable angle for haptic lug landing stability using the 360° global ciliary sulcus depth difference.

[0050] Existing ICL implantation techniques suffer from large errors, unstable arch height prediction, and easy lens misalignment and rotation. Traditional methods, such as using the STS method (measurement of horizontal and vertical orientation using UBM) to determine the placement method and relying on the surgeon's intuition to adjust the rotation angle to adjust the arch height, are prone to inaccuracies. This invention uses depth difference to determine the optimal angle for haptic landing stability, providing an optimized rotation scheme. Further, it involves dividing the LL (Limbed Array) into zones based on lateral depth difference, balancing the four haptic regions, and calculating the ICL rotation adjustment points. This calculation considers the diagonal points between the four ICL haptic legs. Figure 5 The labels AC and BD are shown. A greater difference in lateral depth results in a more stable clasp and reduces the likelihood of postoperative rotational displacement. For example... Figure 4 As shown, taking two points, depth value 1 and depth value 2, as an example: the depth value is defined as the distance between the tissue surface on the LL and the BFLS. The formula for calculating the depth difference is (depth value 1 - depth value 2). Figure 6 As shown, the lateral depth difference within the same horizontal area, such as using D1 to D... 360 Each scale value, namely D n and D n+1 The angle difference between them is 1°, which can be used to calculate the depth difference within a set angle. For example, if the setting is within a range of 45° to 48°, take D. 45 D 46 D 47 D 48 D 49 The depth values ​​at the site are calculated by integrating the various values, and can be expressed using various mathematical methods such as the standard deviation of discrete intervals, showing the depth difference within the region (2° to 5° arc angle). In a specific implementation, a depth difference with a mean greater than 200-300 micrometers within the 2° to 5° range is marked as a high depth difference; a depth difference of 100-200 micrometers is a medium depth difference; and a depth difference less than 100 micrometers is a low depth difference. The high depth difference represents the optimal landing position for the lens haptic during intraoperative lens rotation and positioning, providing a more ideal and stable fixation effect and avoiding unexpected postoperative secondary rotation. Conversely, low depth differences should be avoided as they can cause instability in lens haptic fixation, leading to concerns about rotation or displacement. Based on the depth difference, optimized selectable lens rotation sites can be obtained. In the calculation, the number of analyzed sites can range from 20 to 500.

[0051] Based on the positions of the four haptics ABCD of the intraocular lens (e.g. Figure 5As shown in the figure, the stability of each loop can be obtained from the depth difference distribution along the LL line. The stability of the four loops is summed to obtain a stability score for a set of loop position combinations. The stability scores are sorted from high to low, and the higher the ranking, the more ideal the loop position combination, and the better it is in the subsequent voting calculation for crystal matching. The stability can be designed as needed, with higher depth differences resulting in higher stability.

[0052] In the lens matching module, lens inventory data is acquired. Based on the pre-obtained arch height prediction range and the ideal haptic position combination sequence, a voting matching algorithm is used to select the best-fitting intraocular lens (IOL) and implantation rotation scheme for adjusting the arch height from the lens inventory. The best-fitting IOL prioritizes meeting the arch height prediction range and has the ideal haptic position combination with a higher stability score. In this lens matching module, the arch height prediction range is the priority target, ultimately obtaining at least one best-fitting IOL and its implantation rotation scheme for the doctor to choose from. The main function of the voting matching algorithm is to obtain the most stable depth difference and the most suitable rotation angle, with rotation angle being the priority, ideally considering both. After selecting the appropriate size and rotation scheme, the system checks with the manufacturer's lens library to see if there is a matching size and astigmatic cylinder lens (TICL) in stock; if not, the calculation is downgraded.

[0053] The arch height prediction range can be obtained using existing known methods, such as AI big data models like image recognition DNN (Deep Neural Network), RNN (Recurrent Neural Network), CNN (Convolutional Neural Network), or other various computer-automated methods. This involves predicting the diagonals of the four haptics of the ICL intraocular lens and the 360° real sulcus tosulcus (RSTS) determined by the haptic landing lines. Different sizes of ICLs have different arch height prediction ranges, and furthermore, different ocular physiological accommodation states also result in different arch height prediction ranges. In a specific implementation, the radial distances of the ABCD diagonals of four sizes of ICLs (12.1mm, 12.6mm, 13.2mm, and 13.7mm) can be obtained (e.g.,...). Figure 5(As shown) is the predicted range of arch height under RSTS association. The predicted range of arch height obtained by AI can be further optimized to the target safe arch height range. Among them, the machine learning training of big data can be carried out by inputting data from different devices commonly used in daily clinical settings or multiple sets of data measured by the same device under different lighting or external stimuli, so as to improve the accuracy of arch height prediction in the later machine learning. For example, before surgery, a 3D topographic map of the high ciliary sulcus region can be obtained using a three-dimensional anterior segment measurement device such as 3D UBM, and the rotation design of ICL implantation can be carried out. During the follow-up examination after surgery, a more convenient non-contact device is used to measure the changes in parameters, such as using Scheimpflug rotational imaging, anterior segment OCT and other devices. The actual measured arch height related parameters are then input into the machine learning database to continuously accumulate machine learning training data.

[0054] Acquire crystal inventory data and automatically match as needed TICL (size, spherical, cylindrical, and rotatable astigmatic axis all meet the requirements) or ICL (size and spherical) where the parameters meet the target safety arch height range and the ideal loop position combination is earlier in the ideal loop position combination sequence. If no match is found, the ideal loop position combination is reduced, for example, the overall stability score of 4 loops is reduced, and a downgrade calculation is performed until a crystal in the crystal library is matched.

[0055] In the implementation example of the downgrade calculation, ideally, all four ICL haptics should land simultaneously in the high depth difference (LL) region, ensuring the most stable rotational position of the ICL. However, in reality, given the limited structure of the eyeball, only two haptics can simultaneously be in the high depth difference condition, while the other two haptics have a low-to-medium depth difference. Therefore, the lens matching module uses a voting matching algorithm to generate an implantation rotation scheme, achieving balanced depth difference fitting calculations for each of the four haptics. The goal is to match the four haptics to the region with the largest possible simultaneous depth difference, thereby determining the selected angle.

[0056] like Figure 7 Scheme A shown Figure 7 a) and Option B Figure 7 (b) Using the matching operation of the crystal matching module, scheme A was chosen as the final implantation and rotation scheme. Although a 45° counterclockwise rotation after implantation is not the most stable, TICL astigmatism lenses have crystal inventory, making it a compromise and optimal solution. While a 90° counterclockwise rotation after implantation achieves the most stable arch height, with all four loops located at high depth differences, TICL astigmatism lenses do not have a crystal inventory that addresses this angle's astigmatism axis design or dimensions. Even if the arch height is stable, it might be too low or too high. Therefore, scheme B was abandoned. Figure 8 The diagram shows the implantation location of the lens using scheme A.

[0057] like Figure 9 As shown, the workflow of the aforementioned intelligent assisted lens-attaching system for phakic intraocular lenses includes: constructing a 3D topographic map of the ciliary sulcus region based on 3D structural data through AI 3D image semantic analysis; extracting the ciliary sulcus line LS; fitting an imaginary best-fitting ciliary sulcus line BFLS that conforms to the surface of LS; using BFLS as a reference; calculating the haptic landing line LL through vertical depth difference; and listing the optimal sequence of possible ideal haptic position combinations through lateral depth difference; based on pre-obtained multiple arch height prediction ranges, lens inventory data, and theoretical... The ideal haptic position combination sequence is used for voting and matching to obtain a suitable intraocular lens and a corresponding optimized, highly stable rotation and positioning scheme. In the voting and matching process, based on the pre-obtained arch height prediction range and the ideal haptic position combination with the highest stability score in the ideal haptic position combination sequence, the most suitable intraocular lens size is determined. Based on the lens inventory data, it is determined whether there is a matching lens in stock. If so, the best-fitting intraocular lens and implantation rotation scheme are obtained. If not, a downgrade calculation is performed based on the ideal haptic position combination sequence.

[0058] like Figure 10 As shown, in this intelligent assisted lens ordering system, each ICL implantation eye structure measurement is updated and saved into the AI ​​big data database, realizing a closed-loop process for AI training, so as to train and update the algorithm model used in the prediction and matching process and improve accuracy.

[0059] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A smart assisted lens-attaching system for phakic intraocular lenses, characterized in that, include: The loop landing line acquisition module is used to acquire three-dimensional structural data of the anterior and posterior chambers. Based on the three-dimensional structural data, a 3D topographic map of the ciliary sulcus region is constructed through AI three-dimensional image semantic analysis. An imaginary best-fit ciliary sulcus line that fits the actual ciliary sulcus surface is obtained. The loop landing line is calculated using the best-fit ciliary sulcus line as a reference. The coordinates of the points on the loop landing line consist of lateral depth and vertical depth. The ideal haptic determination module is used to calculate the lateral depth difference between points on the haptic landing line based on the lateral depth, and simultaneously obtain the ideal haptic position combination sequence of the four haptics of the intraocular lens based on the true STS of the haptic landing line. In this sequence, each ideal haptic position combination corresponds to a stability score, and each ideal haptic position combination is sorted from high to low according to the stability score. The lens matching module is used to acquire lens inventory data. Based on the pre-obtained arch height prediction range and the ideal haptic position combination sequence, the module uses a voting matching algorithm to obtain the best-fit intraocular lens and the implantation rotation scheme for adjusting the arch height from the lens inventory. The best-fit intraocular lens preferentially meets the arch height prediction range and has the ideal haptic position combination with a higher stability score. In the voting matching algorithm, the most suitable intraocular lens size is determined based on the pre-obtained arch height prediction range and the ideal haptic position combination with the highest stability score in the ideal haptic position combination sequence. Based on the lens inventory data, it is determined whether there is a matching lens inventory. If so, the best-fit intraocular lens and implantation rotation scheme are obtained. If not, a downgrade calculation is performed based on the ideal haptic position combination sequence.

2. The intelligent assisted lens-attaching system for phakic intraocular lenses according to claim 1, characterized in that, The 3D topographic map of the ciliary groove region is the area formed by the connection of the surfaces of the posterior chamber structure.

3. The intelligent assisted lens-attaching system for phakic intraocular lenses according to claim 1, characterized in that, The central axis of the best-fit ciliary sulcus line is parallel to the optical axis, visual axis, or central axis of the eyeball.

4. The intelligent assisted lens-attaching system for phakic intraocular lenses according to claim 1, characterized in that, The points on the loop landing line are either points where the probability of loop landing is within a certain probability range or points where the equilibrium probability of landing of the four loops of the intraocular lens is within a certain probability range.

5. The intelligent assisted lens-attaching system for phakic intraocular lenses according to claim 4, characterized in that, The points on the landing line of the slack are obtained based on the landing point probability prediction model, which obtains the possible landing probability of the slack at a certain vertical depth.

6. The intelligent assisted lens-attaching system for phakic intraocular lenses according to claim 1, characterized in that, The stability of the ideal haptic position combination is obtained by summing the stability of the four haptics of the intraocular lens. The stability is determined by the lateral depth difference within a set angle on the haptic landing line. The greater the lateral depth difference, the higher the stability.

7. The intelligent assisted lens-attaching system for phakic intraocular lenses according to claim 1, characterized in that, The arch height prediction range is obtained based on an AI big data model, the diagonals of the four haptics of the intraocular lens, and a 360° real STS prediction determined by the haptic landing line. Intraocular lenses of different sizes have different arch height prediction ranges.

8. The intelligent assisted lens-attaching system for phakic intraocular lenses according to claim 1, characterized in that, The optimally fitted intraocular lens is at least one type.

9. The intelligent assisted lens-attaching system for phakic intraocular lenses according to claim 1, characterized in that, The intraocular lens includes an ICL lens without astigmatism or an ICL lens with astigmatism.

Images