CN113935809A - Intelligent assessment auxiliary system and method for orthokeratology lens - Google Patents
Intelligent assessment auxiliary system and method for orthokeratology lens Download PDFInfo
- Publication number
- CN113935809A CN113935809A CN202111219869.1A CN202111219869A CN113935809A CN 113935809 A CN113935809 A CN 113935809A CN 202111219869 A CN202111219869 A CN 202111219869A CN 113935809 A CN113935809 A CN 113935809A
- Authority
- CN
- China
- Prior art keywords
- lens
- difference
- evaluation
- corneal
- topographic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0621—Item configuration or customization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention discloses an intelligent evaluation auxiliary system and method for a corneal plastic lens, wherein the system comprises: the parameter acquisition module is used for acquiring the fitting parameters and the basic characteristics of the patient; a corneal topography database for storing corneal topographic map data before and after fitting; the marking module is used for presetting marks of a real area and a central point on the corneal difference topographic map; the model construction module is used for constructing a corneal plastic lens evaluation auxiliary model according to the lens matching parameters, the basic characteristics, the corneal difference topographic map and the marks of the real treatment area and the central point of the patient; the model evaluation module is used for evaluating the cornea moulding mirror evaluation auxiliary model according to a preset evaluation index and outputting an evaluation result; the system and the method can provide the basis for lens matching, and doctors or optometrists can quickly and accurately provide the processing suggestion for lens matching according to the basis for lens matching so as to ensure the accuracy of lens matching and greatly improve the efficiency of lens matching.
Description
Technical Field
The invention relates to the technical field of orthokeratology lenses, in particular to an intelligent evaluation auxiliary system and method for orthokeratology lenses.
Background
The orthokeratology lens is originated in the United states, is a hard contact lens similar to a contact lens, is worn during sleep at night, enables the radian of the cornea in a central area to become flat, enables the peripheral area to become steep, can correct the refraction state of a central retina, and can correct the hypermetropia defocusing of the peripheral retina, thereby achieving the purpose of effectively controlling the myopia development of children.
At present, the fitting mode of the orthokeratology lens is that a doctor or a optometrist manually carries out multiple trial fitting and fitting evaluation on a trial fitting piece of a user, determines the optimal orthokeratology lens parameters, and then orders and processes the orthokeratology lens. What is more, this method is the individual fitting technique and experience of the doctor or optometrist, and the patient who needs to be matched with the glasses has the problem of being inaccurate and inefficient.
Therefore, it is an urgent need to solve the problems of the art to provide an intelligent evaluation auxiliary system and method for orthokeratology lens to solve the problem of fitting accuracy, improve fitting efficiency, and help patients to obtain orthokeratology lens more conveniently.
Disclosure of Invention
The invention aims to provide an intelligent evaluation auxiliary system and method for a corneal plastic lens, the system is simple in structure, safe, effective, reliable and simple and convenient to operate, the logic of the method is clear, and the accuracy and the efficiency of lens fitting can be effectively improved.
Based on the above purposes, the technical scheme provided by the invention is as follows:
an orthokeratology mirror intelligent assessment auxiliary system, comprising:
the parameter acquisition module is used for acquiring the fitting parameters and the basic characteristics of the patient;
a corneal topography database for storing corneal topographic map data before and after fitting;
the marking module is used for presetting marks of a real area and a central point on the corneal difference topographic map;
the model building module is used for building a corneal plastic lens evaluation auxiliary model according to the lens matching parameters, the basic characteristics, the corneal difference topographic map and the marks of the real treatment area and the central point of the patient;
and the model evaluation module is used for evaluating the cornea moulding mirror evaluation auxiliary model according to preset evaluation indexes and outputting an evaluation result.
Preferably, the method further comprises the following steps:
the model training module is used for training the cornea moulding mirror evaluation auxiliary model;
and the model verification module is used for selecting an optimal model according to the training result.
Preferably, the orthokeratology evaluation auxiliary model comprises:
the region segmentation model is used for performing convolution classification, processing and sampling on the corneal difference topographic maps before and after lens fitting to obtain a processed corneal difference region topographic feature map;
and the central positioning model is used for presetting the central point of the simulation area with the processed topographic feature map of the corneal difference area.
Preferably, the processed topographic map of the corneal differential area comprises:
the axial difference topographic feature map is used for displaying the coverage condition of the simulated area on the pupil area and feeding back the quality of the treatment effect;
and the tangential difference topographic feature map is used for displaying the position of the central point of the simulation area and feeding back the relative state of the lens and the cornea.
Preferably, the model evaluation module comprises: the evaluation indexes of the region segmentation model and the center positioning model.
Preferably, the evaluation index of the region segmentation model is IOU;
the evaluation formula is specifically as follows: IOU ═ B (A ≈ B)/(A ═ U B)
Wherein A is a preset real treatment area, and B is a simulation area displayed by an axial difference topographic feature map.
Preferably, the center positioning model evaluation index is Distance;
the evaluation formula is specifically as follows:
wherein, (x, y) is the coordinate of the preset central point,
and displaying the coordinates of the central point of the simulation area for the tangential difference topographic feature map.
An intelligent assessment auxiliary method for a orthokeratology lens is realized based on an intelligent assessment auxiliary system for the orthokeratology lens, and comprises the following steps:
acquiring lens matching parameters and basic characteristics of a patient and corneal difference topographic maps before and after lens matching;
presetting marks of a real area and a central point in a corneal difference topographic map before and after lens fitting according to the intelligent cornea moulding lens evaluation auxiliary system;
processing corneal difference topographic maps before and after lens fitting according to the corneal shaping lens intelligent evaluation auxiliary system to obtain an axial difference topographic map and a tangential difference topographic map;
evaluating an axial difference topographic feature map and a tangential difference topographic feature map according to preset evaluation parameters in the intelligent evaluation auxiliary system of the orthokeratology mirror, and outputting an evaluation result;
and giving treatment opinions of the patient according to the prescription parameters, the basic characteristics and the evaluation result of the patient.
Preferably, in processing the corneal difference topographic map before and after fitting the lens according to the intelligent corneal remodelling lens evaluation auxiliary system to obtain the axial difference topographic feature map and the tangential difference topographic feature map, the processing mode specifically comprises:
after the cornea difference topographic maps before and after lens preparation are subjected to convolution classification, processing and sampling, acquiring a topographic feature map of a processed cornea difference area and presetting a central point of a simulation area;
the axial difference topographic feature map is used for displaying the coverage condition of the simulation area on the pupil area, and the tangential difference topographic feature map is used for displaying the position of the central point of the simulation area.
Preferably, before acquiring the lens matching parameters, the basic characteristics and the corneal difference topographic map before and after lens matching of the patient, the method further comprises the following steps:
training a cornea moulding mirror evaluation auxiliary model;
and selecting an optimal model according to the training result.
The cornea moulding mirror evaluation auxiliary system provided by the invention is provided with a parameter acquisition module, a cornea topographic map database, a marking module, a model construction module and a model evaluation module. Wherein the corneal topography database is connected with the marking module; the parameter acquisition module and the marking module are connected with the model construction module; the model building module is connected with the model evaluation module. In the actual application process, the acquired cornea difference topographic maps before and after fitting are called from the cornea topographic map database, and a real area and a central point mark are preset in the cornea difference topographic maps before and after fitting; then, constructing a corneal plastic lens evaluation auxiliary model according to the fitting parameters, the basic characteristics, the corneal difference topographic map, a preset real area and the central point mark of the patient; the cornea plastic endoscope evaluation auxiliary model is evaluated through the healing evaluation index, the evaluation result is output, and a doctor or a optometrist can quickly and accurately give a treatment suggestion of endoscope preparation according to the evaluation result, the endoscope preparation parameters of a patient and the basic characteristics, so that the accuracy of endoscope preparation is ensured, and the efficiency of endoscope preparation is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of an intelligent evaluation auxiliary system for a orthokeratology lens according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an intelligent evaluation auxiliary system for orthokeratology lens according to an embodiment of the present invention;
fig. 3 is a flowchart of an auxiliary method for intelligent evaluation of orthokeratology lens according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of U-Net in the region segmentation model according to the embodiment of the present invention;
fig. 5 is a schematic structural diagram of an FCN in the region segmentation model according to the embodiment of the present invention;
fig. 6 is a schematic structural diagram of a VGG16 in the center positioning model according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Embodiments of the present invention are written in a progressive manner.
The embodiment of the invention provides a cornea shaping mirror evaluation auxiliary system and a cornea shaping mirror evaluation auxiliary method. Mainly solves the technical problems of inaccuracy and inefficiency in the artificial cornea matching and moulding mirror fitting in the prior art.
An orthokeratology mirror intelligent assessment auxiliary system, comprising:
the parameter acquisition module is used for acquiring the fitting parameters and the basic characteristics of the patient;
a corneal topography database for storing corneal topographic map data before and after fitting;
the marking module is used for presetting marks of a real area and a central point on the corneal difference topographic map;
the model building module is used for building a corneal plastic lens evaluation auxiliary model according to the lens matching parameters, the basic characteristics, the corneal difference topographic map and the marks of the real treatment area and the central point of the patient;
and the model evaluation module is used for evaluating the cornea moulding mirror evaluation auxiliary model according to preset evaluation indexes and outputting an evaluation result.
The cornea moulding mirror evaluation auxiliary system provided by the invention is provided with a parameter acquisition module, a cornea topographic map database, a marking module, a model construction module and a model evaluation module. Wherein the corneal topography database is connected with the marking module; the parameter acquisition module and the marking module are connected with the model construction module; the model building module is connected with the model evaluation module. In the actual application process, the acquired cornea difference topographic maps before and after fitting are called from the cornea topographic map database, and a real area and a central point mark are preset in the cornea difference topographic maps before and after fitting; then, constructing a corneal plastic lens evaluation auxiliary model according to the fitting parameters, the basic characteristics, the corneal difference topographic map, a preset real area and the central point mark of the patient; the cornea plastic endoscope evaluation auxiliary model is evaluated through the healing evaluation index, the evaluation result is output, and a doctor or a optometrist can quickly and accurately give a treatment suggestion of endoscope preparation according to the evaluation result, the endoscope preparation parameters of a patient and the basic characteristics, so that the accuracy of endoscope preparation is ensured, and the efficiency of endoscope preparation is greatly improved.
Preferably, the method further comprises the following steps:
the model training module is used for training the cornea moulding mirror evaluation auxiliary model;
and the model verification module is used for selecting an optimal model according to the training result.
In the actual application process, in order to ensure the accuracy of the orthokeratology lens evaluation auxiliary system, a model training module and a model verification module are further arranged and act together to select an optimal model. In general, the training time node is adjusted by combining the reexamination requirement of the patient, so that the peak period of the doctor can be avoided, and the model can be optimally trained when the patient is less. The updated algorithm needs to achieve higher accuracy. The data will be as follows 8: 1: 1, dividing the model into a training set, a verification set and a test set, selecting an optimal model and corresponding hyper-parameters thereof by a cross-validation method, finally selecting the model which shows the optimal performance in the test set from a plurality of models, and updating the model in the system.
Preferably, the orthokeratology evaluation auxiliary model comprises:
the region segmentation model is used for performing convolution classification, processing and sampling on the corneal difference topographic maps before and after lens fitting to obtain a processed corneal difference region topographic feature map;
and the central positioning model is used for presetting the central point of the simulation area with the processed topographic feature map of the corneal difference area.
In the actual application process, the basic framework of the region segmentation model is based on a U-Net segmentation network, modification is made according to the specificity of a segmentation target, an attention mechanism is added, and the weight of a key region is expanded. The U-Net basic framework is shown in FIG. 1. Besides U-Net, a Full Convolution Network (FCN) is set as a basic model, and a supplementary residual error network structure is used for improving the segmentation effect of the FCN. The FCN basic framework is shown in fig. 2.
For an image with any size, the FCN performs convolution classification (pixel-level classification) on each pixel, the network structure of the image is eight layers of convolution layers, one-step up-sampling operation is added, the image is input as an original image, and the image is output as +1 (background) feature maps with the same size as the original image in the number of categories. Of the first five convolutional layers (with one layer pooled), the first layer output feature size is 1/4 for the original, the second layer 1/8, and the fifth layer 1/16. The depths (the number of feature maps) also increase and decrease, and are respectively 96, 256, 384 and 256. The convolutional layer with six, seven and eight layers is formed by changing the fully-connected layer in the original CNN structure into a convolutional layer with different convolutional kernel depths, and the size of an output characteristic graph is 1/32. The depths of the sixth, seventh and eighth layers are 4096, 4096 and 1000, respectively. All of the above depth dimensions should be adjustable in practice. The upsampling operation is intended to reduce the low resolution image to the size of the original image to show where the different classes (parts) are divided. Directly up-sampling the 1/32 size feature map obtained finally (in the fifth pooling step) by a factor of 32; or performing two-time upsampling on the final 1/32 size characteristic diagram, adding the upsampled result of the fourth step, and performing 16-time upsampling; or the final 1/32 size signature is upsampled four times, the pooled 1/16 size signature of the fourth step is upsampled two times, and the 1/8 size signature of the third step is added together and upsampled 8 times. Finally, the feature mark graph with the same size as the original graph can be obtained. Of the three methods, the greater the number of pooled layers combined, the better the performance.
The structure of the U-Net network is as follows: four layers of 2 × 2 maximum pooling and four layers of twice upsampling, wherein each layer has two steps of 3 × 3 convolution operation, and finally one step of 1 × 1 convolution is carried out to obtain a plurality of characteristic graphs of pixel categories. Each layer of pooling can obtain a feature map of the original image with half the size, and the convolution depth (namely the depth of the feature map) is doubled; each layer of upsampling obtains a feature map with the size of the previous layer of input feature map being doubled, the convolution depth is reduced by half (namely the depth of the feature map is reduced by half), and the feature map obtained by the same level of pooling is cut (the standard is the size of the feature map after upsampling) and added (fused) with the feature map.
Compared with FCN, U-Net has more upsampling layers and better utilizes the characteristic information of each layer during pooling, but the quality of the model is related to the practical application image.
The basic framework of the central positioning model is based on a Convolutional Neural Network (CNN), the specific function is to preset a topographic feature map of a processed corneal difference region to a central point of a simulation region, and the optimal model is found to serve as the positioning model by setting CNNs of different levels including (VGG11, VGG13, VGG16, VGG19, AlexNet and the like). In the present embodiment, VGG16 is an optimal model.
Preferably, the processed topographic map of the corneal differential area comprises:
the axial difference topographic feature map is used for displaying the coverage condition of the simulated area on the pupil area and feeding back the quality of the treatment effect;
and the tangential difference topographic feature map is used for displaying the position of the central point of the simulation area and feeding back the relative state of the lens and the cornea.
The topographic map of the corneal difference region is the difference between the topographic maps after wearing the orthokeratology lens and before wearing the orthokeratology lens, and the difference data between the topographic maps are expressed in the form of images and are called as a difference map. In the actual application process, the axial difference topographic map is used for evaluating the influence of the range of the optical effect generated by the treatment area on the visual effect, the coverage condition of the treatment area on the pupillary area is mainly observed, and the quality of the treatment effect is fed back through the overlapped area proportion of the treatment area and the pupillary area and the actual treatment experience of a patient; the tangential difference topographic map is used for evaluating the position of the treatment area on the cornea, and indirectly judges the relative state of the lens and the cornea when the cornea shaping mirror is worn, and mainly observes the position of the central point of the treatment area.
Preferably, the model evaluation module comprises: the evaluation indexes of the region segmentation model and the center positioning model.
In the actual application process, the model evaluation module is preset with an area segmentation model evaluation index and a center positioning model evaluation index. And obtaining an evaluation result according to the two evaluation indexes to be used as the basis for the prescription of the doctor or optometrist.
Preferably, the evaluation index of the region segmentation model is IOU;
the evaluation formula is specifically as follows: IOU ═ B (A ≈ B)/(A ═ U B)
Wherein A is a preset real treatment area, and B is a simulation area displayed by an axial difference topographic feature map.
In the actual application process, the IOU value is obtained through calculation, and the higher the IOU value is, the higher the coincidence rate of the two areas is, and the stronger the model capability is.
Preferably, the center positioning model evaluation index is Distance;
the evaluation formula is specifically as follows:
wherein, (x, y) is the coordinate of the preset central point,
and displaying the coordinates of the central point of the simulation area for the tangential difference topographic feature map.
In the actual application process, the Distance value is obtained through calculation, and the smaller the Distance value is, the closer the Distance between two points is, the stronger the model capability is.
An intelligent assessment auxiliary method for a orthokeratology lens is realized based on an intelligent assessment auxiliary system for the orthokeratology lens, and comprises the following steps:
s1, acquiring lens matching parameters and basic characteristics of a patient and corneal difference topographic maps before and after lens matching;
s2, presetting marks of a real area and a central point in a corneal difference topographic map before and after lens preparation according to the intelligent cornea moulding lens evaluation auxiliary system;
s3, processing corneal difference topographic maps before and after lens preparation according to the corneal shaping lens intelligent evaluation auxiliary system to obtain an axial difference topographic map and a tangential difference topographic map;
s4, evaluating an axial difference topographic feature map and a tangential difference topographic feature map according to preset evaluation parameters in the intelligent evaluation auxiliary system of the orthokeratology mirror, and outputting an evaluation result;
and S5, giving a treatment suggestion of the patient according to the matching parameters, the basic characteristics and the evaluation result of the patient.
In the actual application process, the parameters and the basic characteristics of the patient during lens fitting and the corneal difference topographic map before and after lens fitting are obtained; presetting marks of a real area and a central point for a cornea difference topographic map before and after lens preparation; uploading the corneal difference topographic maps before and after fitting to an intelligent assessment auxiliary system of the orthokeratology lens, and processing the corneal difference topographic maps by the intelligent assessment auxiliary system of the orthokeratology lens to generate an axial difference topographic feature map and a tangential difference topographic feature map; evaluating the axial difference topographic feature map and the tangential difference topographic feature map through preset parameters in the intelligent cornea moulding mirror evaluation auxiliary system and outputting an evaluation result; the doctor or optometrist gives the patient treatment opinions on the prescription according to the prescription parameters, basic characteristics and evaluation results of the patient. The method has clear logic and simple steps, can avoid the technical problem of inaccurate manual lens matching, and improves the efficiency of lens matching.
Preferably, in processing the corneal difference topographic map before and after fitting the lens according to the intelligent corneal remodelling lens evaluation auxiliary system to obtain the axial difference topographic feature map and the tangential difference topographic feature map, the processing mode specifically comprises:
after the cornea difference topographic maps before and after lens preparation are subjected to convolution classification, processing and sampling, acquiring a topographic feature map of a processed cornea difference area and presetting a central point of a simulation area;
the axial difference topographic feature map is used for displaying the coverage condition of the simulation area on the pupil area, and the tangential difference topographic feature map is used for displaying the position of the central point of the simulation area.
In the actual application process, the specific operation processes of convolution classification, processing and sampling are realized based on the region segmentation model, which is described in detail and is not described herein again.
Preferably, before acquiring the lens matching parameters, the basic characteristics and the corneal difference topographic map before and after lens matching of the patient, the method further comprises the following steps:
training a cornea moulding mirror evaluation auxiliary model;
and selecting an optimal model according to the training result.
In the actual application process, before step S1, a step of optimizing the model is further included, and the specific operation process is as follows: when the picture size is (H, W, C), an auxiliary matrix of (H, W, 1) is initialized, each value in the matrix obeys the uniform distribution of (0, 1), and the matrix is spliced with the picture into a matrix of (H, W, C +1) to enter a segmentation model of U-Net, FCN and the like. Meanwhile, the auxiliary matrix is fully connected with the real segmentation result, and a new auxiliary matrix is obtained through back propagation.
In the embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the modules is only one division of logical functions, and other divisions may be realized in practice, such as: multiple modules or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or modules may be electrical, mechanical or other.
In addition, all functional modules in the embodiments of the present invention may be integrated into one processor, or each module may be separately used as one device, or two or more modules may be integrated into one device; each functional module in each embodiment of the present invention may be implemented in a form of hardware, or may be implemented in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by program instructions and related hardware, where the program instructions may be stored in a computer-readable storage medium, and when executed, the program instructions perform the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The present invention provides an intelligent evaluation auxiliary system and method for orthokeratology lens. The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An orthokeratology mirror intelligent assessment auxiliary system, comprising:
the parameter acquisition module is used for acquiring the fitting parameters and the basic characteristics of the patient;
a corneal topography database for storing corneal topographic map data before and after fitting;
the marking module is used for presetting marks of a real area and a central point on the corneal difference topographic map;
the model construction module is used for constructing a corneal plastic lens evaluation auxiliary model according to the lens matching parameters, the basic characteristics, the corneal difference topographic map and the marks of the real treatment area and the central point of the patient;
and the model evaluation module is used for evaluating the cornea moulding mirror evaluation auxiliary model according to a preset evaluation index and outputting an evaluation result.
2. The orthokeratology lens intelligent assessment assistance system of claim 1, further comprising:
the model training module is used for training the orthokeratology lens evaluation auxiliary model;
and the model verification module is used for selecting an optimal model according to the training result.
3. The orthokeratology lens intelligent assessment assistance system of claim 1, wherein the orthokeratology lens assessment assistance model comprises:
the region segmentation model is used for performing convolution classification, processing and sampling on the corneal difference topographic maps before and after lens fitting to obtain a processed corneal difference region topographic feature map;
and the central positioning model is used for presetting a central point of a simulation area according to the processed topographic feature map of the corneal difference area.
4. The orthokeratology lens intelligent assessment assistance system of claim 3, wherein the processed corneal topographic map of differential area comprises:
the axial difference topographic feature map is used for displaying the coverage condition of the simulated area on the pupil area and feeding back the quality of the treatment effect;
and the tangential difference topographic feature map is used for displaying the position of the central point of the simulation area and feeding back the relative state of the lens and the cornea.
5. The orthokeratology lens intelligent assessment assistance system of claim 3, wherein the model evaluation module comprises: the evaluation indexes of the region segmentation model and the center positioning model.
6. The intelligent evaluation auxiliary system for orthokeratology lens of claim 5, wherein the region segmentation model evaluation index is IOU;
the evaluation formula is specifically as follows: IOU ═ B (A ≈ B)/(A ═ U B)
Wherein A is a preset real treatment area, and B is a simulation area displayed by an axial difference topographic feature map.
7. The intelligent evaluation auxiliary system for orthokeratology lens of claim 5, wherein the central positioning model evaluation index is Distance;
the evaluation formula is specifically as follows:
wherein, (x, y) is the coordinate of the preset central point,
and displaying the coordinates of the central point of the simulation area for the tangential difference topographic feature map.
8. An intelligent assessment auxiliary method for a orthokeratology lens is realized based on an intelligent assessment auxiliary system for the orthokeratology lens, and is characterized by comprising the following steps:
acquiring lens matching parameters and basic characteristics of a patient and corneal difference topographic maps before and after lens matching;
presetting marks of a real area and a central point in a corneal difference topographic map before and after lens fitting according to the intelligent cornea shaping lens evaluation auxiliary system;
processing the corneal difference topographic map before and after lens fitting according to the corneal shaping lens intelligent evaluation auxiliary system to obtain an axial difference topographic feature map and a tangential difference topographic feature map;
evaluating the axial difference topographic feature map and the tangential difference topographic feature map according to preset evaluation parameters in the intelligent evaluation auxiliary system of the orthokeratology mirror, and outputting an evaluation result;
and giving treatment opinions of the patient according to the parameters, the basic characteristics and the evaluation result of the patient.
9. The intelligent evaluation auxiliary method for orthokeratology lens of claim 5, wherein the processing of the corneal topographic map before and after fitting according to the intelligent evaluation auxiliary system for orthokeratology lens to obtain the axial topographic map of difference and the tangential topographic map of difference is specifically as follows:
after the cornea difference topographic maps before and after lens preparation are subjected to convolution classification, processing and sampling, acquiring a topographic feature map of a processed cornea difference area and presetting a central point of a simulation area;
the axial difference topographic feature map is used for displaying the coverage condition of a simulation area on a pupil area, and the tangential difference topographic feature map is used for displaying the position of a center point of the simulation area.
10. The intelligent assessment auxiliary method for orthokeratology lens as claimed in claim 8, further comprising the following steps before obtaining the fitting parameters, basic characteristics and corneal topographic difference before and after fitting of the lens of the patient:
training the orthokeratology evaluation auxiliary model;
and selecting an optimal model according to the training result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111219869.1A CN113935809A (en) | 2021-10-20 | 2021-10-20 | Intelligent assessment auxiliary system and method for orthokeratology lens |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111219869.1A CN113935809A (en) | 2021-10-20 | 2021-10-20 | Intelligent assessment auxiliary system and method for orthokeratology lens |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113935809A true CN113935809A (en) | 2022-01-14 |
Family
ID=79280659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111219869.1A Pending CN113935809A (en) | 2021-10-20 | 2021-10-20 | Intelligent assessment auxiliary system and method for orthokeratology lens |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113935809A (en) |
-
2021
- 2021-10-20 CN CN202111219869.1A patent/CN113935809A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100504510C (en) | Ophthalmic lenses without joint part and methods for making same | |
| US9341867B1 (en) | Methods of designing and fabricating custom-fit eyeglasses using a 3D printer | |
| JP5738276B2 (en) | A method for evaluating the optical properties of ophthalmic lens designs | |
| JP4057531B2 (en) | Glasses / contact lens selection system and method | |
| CN104335103B (en) | A method for providing a personalized spectacle lens optical system for a wearer | |
| CN104618710B (en) | Dysopia correction system based on enhanced light field display | |
| CN103930821B (en) | For providing the method for the optical system of lens and for the method manufacturing lens | |
| CN105164684A (en) | System for providing an ophthalmic lens | |
| CN111862009A (en) | Classification method of fundus OCT images and computer-readable storage medium | |
| WO2020126514A1 (en) | A method and device for predicting evolution over time of a vision-related parameter | |
| CN108375842B (en) | Lens conforming to retinal resolution, prescription therefor and method of manufacture | |
| CN108235778B (en) | Calibration method and device based on cloud computing, electronic equipment and computer program product | |
| WO2020126513A1 (en) | A method and device for building a model for predicting evolution over time of a vision-related parameter | |
| CN102171600B (en) | Lens design simplification process | |
| CN111160431A (en) | Method and device for identifying keratoconus based on multi-dimensional feature fusion | |
| CN113935809A (en) | Intelligent assessment auxiliary system and method for orthokeratology lens | |
| De Cunha et al. | Measurement of corneal topography in keratoconus | |
| US11256110B2 (en) | System and method of utilizing computer-aided optics | |
| CN112946922B (en) | Method for designing free-form surface progressive lens with astigmatism correction function and lens | |
| Rojo et al. | Generalized ray tracing method for the calculation of the peripheral refraction induced by an ophthalmic lens | |
| WO2016192565A1 (en) | Individual eye use monitoring system | |
| JP2023537034A (en) | Improved calculation of ophthalmic lenses | |
| WO2019178862A1 (en) | Lens complying with retina resolution ratio, and fitting prescription and manufacturing method therefor | |
| CN114730101B (en) | System and method for adjusting inventory eyeglass frames using 3D scanning of facial features | |
| CN114898833B (en) | Myopia prevention and control axle appearance data intelligent management system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |