CN113822928B

CN113822928B - Corneal topography reconstruction method and device

Info

Publication number: CN113822928B
Application number: CN202111386007.8A
Authority: CN
Inventors: 程得集; 牛海涛
Original assignee: Hangzhou Mocular Medical Technology Inc
Current assignee: Hangzhou Mocular Medical Technology Inc
Priority date: 2021-11-22
Filing date: 2021-11-22
Publication date: 2022-03-15
Anticipated expiration: 2041-11-22
Also published as: CN113822928A

Abstract

The embodiment of the invention discloses a corneal topography reconstruction method and a corneal topography reconstruction device. The method comprises the following steps: acquiring an image to be reconstructed; inputting the image to be reconstructed into a segmentation model to perform segmentation of a Placido black-and-white ring so as to obtain a segmentation result; extracting a white ring effective outline from the segmentation result; sequencing the white ring effective outlines to obtain a sequencing result; acquiring sampling points from the sequencing result; and reconstructing a corneal topography by taking the sampling points as input quantities of the reconstructed corneal physical value. By implementing the method provided by the embodiment of the invention, the corneal topography can adapt to complex environmental light conditions and complex and various corneal shapes, and the method is high in segmentation precision, high in consistency and strong in adaptability.

Description

Corneal topography reconstruction method and device

Technical Field

The invention relates to a computer, in particular to a corneal topography reconstruction method and a corneal topography reconstruction device.

Background

In the field of ophthalmic medical treatment, a corneal topography instrument is one of important instruments for measuring the shape of a cornea, can accurately measure the surface curvature parameters of the cornea, and presents the measurement result in a digital topography mode, namely the measurement result is presented in the corneal topography mode, so that the corneal topography instrument has an important guiding function on corneal contact lens inspection, corneal disease diagnosis and postoperative recovery evaluation.

However, the existing corneal topography reconstruction scheme adopts a fixed template, and the measurement result is manually split and then input into the fixed template for presentation, so that the method cannot adapt to various corneal conditions in people, and the reconstruction algorithm has poor adaptability and accuracy.

Therefore, it is necessary to design a new method that can realize a corneal topography adaptable to complicated environmental light conditions and complicated and various corneal shapes, and that has high segmentation accuracy, high consistency, and strong adaptability.

Disclosure of Invention

The invention aims to overcome the defects of the prior art and provides a corneal topography reconstruction method and a corneal topography reconstruction device.

In order to achieve the purpose, the invention adopts the following technical scheme: a corneal topography reconstruction method comprising:

acquiring an image to be reconstructed;

inputting the image to be reconstructed into a segmentation model to perform segmentation of a Placido black-and-white ring so as to obtain a segmentation result;

extracting a white ring effective outline from the segmentation result;

sequencing the white ring effective outlines to obtain a sequencing result;

acquiring sampling points from the sequencing result;

and reconstructing a corneal topography by taking the sampling points as input quantities of the reconstructed corneal physical value.

The further technical scheme is as follows: the segmentation model is obtained by training a convolutional neural network model by using a Placido ring cornea image with segmentation labels of Placido black-white rings as a sample set.

The further technical scheme is as follows: the segmentation model is obtained by training a convolutional neural network model by taking a Placido ring cornea image with segmentation labels of Placido black-white rings as a sample set, and comprises the following steps:

collecting a Placido ring cornea image of human eyes, and carrying out segmentation and labeling on a Placido black-white ring to obtain a sample set;

performing data enhancement on the sample set to form a processed sample set;

and training and testing the convolutional neural network model by using the processed sample set to obtain a segmentation model.

The further technical scheme is as follows: the data enhancing the sample set to form a processed sample set includes:

and carrying out geometric transformation on the sample set, and carrying out color transformation on the sample set after the geometric transformation to obtain a processed sample set.

The further technical scheme is as follows: extracting a white ring effective contour from the segmentation result, wherein the extracting comprises the following steps;

and filtering the white ring area in the segmentation result by adopting edge detection and geometric conditions to obtain a white ring effective outline.

The further technical scheme is as follows: the sorting the white ring effective outlines to obtain a sorting result includes:

determining an image point where a fixation lamp is located in the image at the detection position as a Placido ring central point;

calculating the distance between each point of the white ring effective contour and the center point of the Placido ring to obtain a calculation result;

and sequencing each point in the white ring effective contour from large to small according to the calculation result to obtain a sequencing result.

The further technical scheme is as follows: the obtaining of the sampling points from the sorting result includes:

establishing a polar line equation by taking the central point of the Placido ring as an origin and a certain step angle;

and calculating the intersection point of the contour formed by all polar lines in the circumferential direction and each point in the sequencing result by using the polar line equation to obtain a sampling point.

The present invention also provides a corneal topography reconstruction device comprising:

the image acquisition unit is used for acquiring an image to be reconstructed;

the segmentation unit is used for inputting the image to be reconstructed into a segmentation model to perform Placido black-and-white ring segmentation so as to obtain a segmentation result;

an extraction unit, configured to extract a white-ring effective contour from the segmentation result;

the sorting unit is used for sorting the white ring effective outlines to obtain a sorting result;

the sampling point acquisition unit is used for acquiring sampling points from the sequencing result;

and the reconstruction unit is used for reconstructing a corneal topography by taking the sampling points as input quantities of reconstructed corneal physical values.

Compared with the prior art, the invention has the beneficial effects that: the method comprises the steps of adopting a Placido ring corneal image with Placido black-and-white ring segmentation labels to segment an image to be reconstructed by a segmentation model obtained by training a convolutional neural network, extracting a white ring effective profile from a segmentation result, sequencing distances of all points on the profile, and collecting corresponding sampling points to obtain an input quantity of a reconstructed corneal physical value so as to construct a corneal topographic map, and training the segmentation model through a large number of data-enhanced images, so that the corneal topographic map can adapt to complex environmental light conditions and complex and diverse corneal shapes, and is high in segmentation precision, high in consistency and strong in adaptability.

The invention is further described below with reference to the accompanying drawings and specific embodiments.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic view of an application scenario of a corneal topography reconstruction method according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of a corneal topography reconstruction method according to an embodiment of the present invention;

FIG. 3 is a schematic sub-flow chart of a corneal topography reconstruction method according to an embodiment of the present invention;

FIG. 4 is a schematic sub-flow chart of a corneal topography reconstruction method provided by an embodiment of the present invention;

FIG. 5 is a schematic sub-flow chart of a corneal topography reconstruction method according to an embodiment of the present invention;

fig. 6 is a schematic block diagram of a corneal topography reconstruction apparatus provided in an embodiment of the present invention;

fig. 7 is a schematic block diagram of a sequencing unit of a corneal topography reconstruction apparatus provided by an embodiment of the present invention;

fig. 8 is a schematic block diagram of a sampling point acquisition unit of the corneal topography reconstruction apparatus provided in the embodiment of the present invention;

FIG. 9 is a schematic block diagram of a computer device provided by an 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 some, not all, embodiments of the present invention. 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.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

Referring to fig. 1 and fig. 2, fig. 1 is a schematic view of an application scenario of a corneal topography reconstruction method according to an embodiment of the present invention. Fig. 2 is a schematic flow chart of a corneal topography reconstruction method provided by an embodiment of the present invention. The corneal topography reconstruction method is applied to a server. The server performs data interaction with the terminal, realizes the segmentation and sampling algorithm by utilizing the convolutional neural network model adopting deep learning, adopts a large amount of cornea image data with different clinical forms as training data, strengthens a training database through an effective data enhancement algorithm to train a segmentation model with high robustness, high adaptability and high accuracy, can adapt to complex environmental light conditions and complex and diverse cornea forms, has high segmentation accuracy and high consistency, and outputs a cornea topographic map to the terminal for presentation.

Fig. 2 is a schematic flow chart of a corneal topography reconstruction method according to an embodiment of the present invention. As shown in fig. 2, the method includes the following steps S110 to S160.

And S110, acquiring an image to be reconstructed.

In this embodiment, the image to be reconstructed refers to a cornea image acquired by a cornea topographer.

And S120, inputting the image to be reconstructed into a segmentation model to perform segmentation of a Placido black-and-white ring so as to obtain a segmentation result.

In this embodiment, the segmentation result refers to a Placido black-and-white ring region and a Placido white-and-white ring region obtained by performing Placido black-and-white ring segmentation on the image to be reconstructed.

In this embodiment, the segmentation model is obtained by training a convolutional neural network model using Placido ring cornea image with a segmentation label of Placido black-and-white ring as a sample set.

In an embodiment, referring to fig. 3, the above-mentioned segmentation model is obtained by training a convolutional neural network model using a Placido ring cornea image with segmentation labels of Placido black and white rings as a sample set, and may include steps S121 to S123.

S121, collecting Placido ring cornea images of human eyes, and carrying out segmentation and labeling of Placido black and white rings to obtain a sample set.

In this embodiment, the sample set is Placido ring cornea image with Placido black and white ring segmentation labels.

Specifically, a large number of Placido ring cornea images of human eyes are collected, and Placido black-and-white ring segmentation and labeling are carried out in a mode of combining a traditional segmentation algorithm and manual labeling.

And S122, performing data enhancement on the sample set to form a processed sample set.

In this embodiment, the processed sample set is an image formed by enhancing the Placido ring cornea image with the Placido black-and-white ring segmentation label.

Specifically, the sample set is geometrically transformed, and the geometrically transformed sample set is color transformed to obtain a processed sample set.

The method comprises the steps of carrying out geometric transformation data enhancement, namely turning, rotating, cutting, deforming, zooming and the like on a sample set, and then carrying out color transformation data enhancement, namely noise, blurring, color transformation, erasing, filling and the like, so that richer and more complex training data can be obtained, the accuracy of model training is improved, and the model can adapt to complex ambient light conditions and complex and various cornea forms when carrying out image segmentation.

And S123, training and testing the convolutional neural network model by using the processed sample set to obtain a segmentation model.

In this embodiment, a processed sample set is first divided into a training set and a test set, a corresponding loss function is constructed together when a convolutional neural network model is constructed, after the convolutional neural network model is trained, loss values are calculated by using the loss function according to data obtained by training and actually labeled contents, and when the loss values are maintained unchanged, that is, the current model is converged, that is, the loss values are basically unchanged and very small, it is also indicated that the current model can be used as a segmentation model, generally, the loss values are relatively large when training is started, the loss values are smaller after training, and if the loss values are not maintained unchanged, it is indicated that the current model cannot be used as a segmentation model, that is, the segmented results are not accurate, and at this time, parameters of each layer in the model are retrained until the loss values are stable and small. And after the training is stable, testing the model by adopting the test set to determine the actual application result of the model.

And S130, extracting a white ring effective contour from the segmentation result.

In the present embodiment, the white ring effective contour refers to a contour image including only a white ring.

Specifically, edge detection and geometric conditions are adopted to filter a white ring area in the segmentation result so as to obtain a white ring effective contour.

The edge detection and geometric filtering of the valid contours belong to the prior art, and are not described in detail here.

S140, sorting the white ring effective outlines to obtain a sorting result.

In this embodiment, the sorting result refers to a result obtained by sorting each point on the white ring effective contour in the order from far to near according to the distance of the image point where the fixation lamp is located in the detected image.

In an embodiment, referring to fig. 4, the step S140 may include steps S141 to S143.

S141, determining an image point where the fixation lamp is located in the detected image as a Placido ring central point.

In this embodiment, the Placido ring center point refers to the image point of the fixation lamp in the detected image.

And S142, calculating the distance between each point of the white ring effective contour and the center point of the Placido ring to obtain a calculation result.

In this embodiment, the calculation result is the distance from each point of the white ring effective contour to the Placido ring center point.

S143, sequencing each point in the white ring effective contour from large to small according to the calculation result to obtain a sequencing result.

And S150, acquiring sampling points from the sequencing result.

In this embodiment, the sampling point is an intersection point of polar line equations established by using the central point of Placido ring as the origin and a certain step angle.

In an embodiment, referring to fig. 5, the step S150 may include steps S151 to S152.

And S151, establishing a polar line equation by taking the central point of the Placido ring as an origin and a certain step angle.

In this embodiment, the polar line equation is an equation constructed with the Placido ring center point as the origin and the set step angle.

S152, calculating the intersection points of the contours formed by all polar lines in the circumferential direction and each point in the sequencing result by using the polar line equation to obtain sampling points.

And S160, reconstructing a corneal topography by taking the sampling points as input quantities of reconstructed corneal physical values.

The input quantity of the physical value of the reconstructed cornea is determined, so that the corneal topography can be reconstructed, and the process belongs to the prior art and is not described herein again.

According to the corneal topography reconstruction method, the segmentation model obtained by training the convolutional neural network is used for segmenting the image to be reconstructed by adopting the Placido ring corneal image with the segmentation label of the Placido black-and-white ring, the segmentation result is subjected to extraction of the effective outline of the white ring, the distance sequence of each point on the outline and collection of the corresponding sampling point so as to obtain the input quantity of the physical value of the reconstructed cornea, the corneal topography is constructed, and the segmentation model is obtained by training the image after a large amount of data is enhanced, so that the corneal topography can adapt to complex environmental light conditions and complex and various corneal shapes, and is high in segmentation precision, high in consistency and strong in adaptability.

Fig. 6 is a schematic block diagram of a corneal topography reconstruction device 300 according to an embodiment of the present invention. As shown in fig. 6, the present invention also provides a corneal topography reconstruction device 300 corresponding to the above corneal topography reconstruction method. The corneal topography reconstruction apparatus 300 includes a unit for performing the above-described corneal topography reconstruction method, and the apparatus may be configured in a server. Specifically, referring to fig. 6, the corneal topography reconstruction apparatus 300 includes an image acquisition unit 301, a segmentation unit 302, an extraction unit 303, a sorting unit 304, a sampling point acquisition unit 305, and a reconstruction unit 306.

An image acquisition unit 301, configured to acquire an image to be reconstructed; a segmentation unit 302, configured to input the image to be reconstructed into a segmentation model to perform Placido black-and-white ring segmentation, so as to obtain a segmentation result; an extracting unit 303, configured to extract a white-ring effective contour from the segmentation result; a sorting unit 304, configured to sort the white ring effective outlines to obtain a sorting result; a sampling point acquisition unit 305 configured to acquire sampling points from the sorting result; and a reconstruction unit 306, configured to reconstruct a corneal topography map by using the sampling points as input quantities for reconstructing a corneal physical value.

In an embodiment, the corneal topography reconstruction device 300 further includes:

and the model determining unit is used for training the convolutional neural network model by using the Placido ring cornea image with the partitioning label of the Placido black-white ring as a sample set to obtain a partitioning model.

In an embodiment, the model determination unit comprises an acquisition subunit, a data enhancer unit and a training subunit.

The acquisition subunit is used for acquiring Placido ring cornea images of human eyes and carrying out segmentation and labeling of Placido black and white rings to obtain a sample set; a data enhancer unit for performing data enhancement on the sample set to form a processed sample set; and the training subunit is used for training and testing the convolutional neural network model by using the processed sample set to obtain a segmentation model.

In an embodiment, the data enhancer unit is configured to perform a geometric transformation on the sample set and perform a color transformation on the geometrically transformed sample set to obtain a processed sample set.

In an embodiment, the extracting unit 303 is configured to filter a white-ring area in the segmentation result by using edge detection and a geometric condition to obtain a white-ring effective contour.

In one embodiment, as shown in fig. 7, the sorting unit 304 includes a center point determining subunit 3041, a distance calculating subunit 3042, and a distance sorting subunit 3043.

A central point determining subunit 3041, configured to determine an image point where the fixation lamp is located in the detected image as a Placido ring central point; a distance calculating subunit 3042, configured to calculate a distance from each point of the white ring effective profile to a Placido ring center point, so as to obtain a calculation result; the distance sorting subunit 3043 is configured to sort, according to the calculation result, each point in the white ring effective contour from large to small to obtain a sorting result.

In an embodiment, as shown in fig. 8, the sample point obtaining unit 305 includes an equation construction subunit 3051 and an intersection determination subunit 3052.

An equation constructing subunit 3051, configured to establish an epipolar equation with a certain step angle by using the Placido ring central point as an origin; and the intersection point determining subunit 3052, configured to calculate, by using the polar line equation, intersection points of contours formed by all polar lines in the circumferential direction and each point in the ordering result, so as to obtain sampling points.

It should be noted that, as will be clear to those skilled in the art, the detailed implementation of the corneal topography reconstruction device 300 and the units can refer to the corresponding description in the foregoing method embodiments, and for the convenience and brevity of description, no further description is provided herein.

The corneal topography reconstruction apparatus 300 may be implemented in the form of a computer program that is executable on a computer device as shown in fig. 9.

Referring to fig. 9, fig. 9 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a server, wherein the server may be an independent server or a server cluster composed of a plurality of servers.

Referring to fig. 9, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.

The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 comprises program instructions that, when executed, cause the processor 502 to perform a corneal topography reconstruction method.

The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.

The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 may be caused to perform a corneal topography reconstruction method.

The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the configuration shown in fig. 9 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation of the computer device 500 to which the present application may be applied, and that a particular computer device 500 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

Wherein the processor 502 is configured to run the computer program 5032 stored in the memory to implement the following steps:

acquiring an image to be reconstructed; inputting the image to be reconstructed into a segmentation model to perform segmentation of a Placido black-and-white ring so as to obtain a segmentation result; extracting a white ring effective outline from the segmentation result; sequencing the white ring effective outlines to obtain a sequencing result; acquiring sampling points from the sequencing result; and reconstructing a corneal topography by taking the sampling points as input quantities of the reconstructed corneal physical value.

The segmentation model is obtained by training the convolutional neural network model by using a Placido ring cornea image with segmentation labels of Placido black-white rings as a sample set.

In an embodiment, the processor 502 specifically implements the following steps when implementing the step of training the convolutional neural network model by using a Placido ring cornea image with a Placido black-and-white ring segmentation label as a sample set, wherein the segmentation model is obtained by:

collecting a Placido ring cornea image of human eyes, and carrying out segmentation and labeling on a Placido black-white ring to obtain a sample set; performing data enhancement on the sample set to form a processed sample set; and training and testing the convolutional neural network model by using the processed sample set to obtain a segmentation model.

In an embodiment, when the processor 502 implements the step of performing data enhancement on the sample set to form a processed sample set, the following steps are specifically implemented:

In an embodiment, when the processor 502 implements the step of extracting the white-ring effective contour from the segmentation result, the following steps are specifically implemented:

In an embodiment, when implementing the step of sorting the white ring effective outlines to obtain a sorting result, the processor 502 specifically implements the following steps:

determining an image point where a fixation lamp is located in the image at the detection position as a Placido ring central point; calculating the distance between each point of the white ring effective contour and the center point of the Placido ring to obtain a calculation result; and sequencing each point in the white ring effective contour from large to small according to the calculation result to obtain a sequencing result.

In an embodiment, when the processor 502 implements the step of obtaining the sampling point from the sorting result, the following steps are specifically implemented:

establishing a polar line equation by taking the central point of the Placido ring as an origin and a certain step angle; and calculating the intersection point of the contour formed by all polar lines in the circumferential direction and each point in the sequencing result by using the polar line equation to obtain a sampling point.

It should be understood that in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It will be understood by those skilled in the art that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program instructing associated hardware. The computer program includes program instructions, and the computer program may be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.

Accordingly, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program, when executed by a processor, causes the processor to perform the steps of:

In an embodiment, when the processor executes the computer program to implement the step of training the convolutional neural network model by using a Placido ring cornea image with a Placido black-and-white ring segmentation label as a sample set, the processor specifically implements the following steps:

In an embodiment, when the processor executes the computer program to implement the step of performing data enhancement on the sample set to form a processed sample set, the following steps are specifically implemented:

In an embodiment, when the step of extracting the white-ring effective contour from the segmentation result is implemented by executing the computer program, the processor specifically implements the following steps:

In an embodiment, when the processor executes the computer program to implement the step of sorting the white-ring valid contours to obtain a sorting result, the processor specifically implements the following steps:

In an embodiment, when the processor executes the computer program to realize the step of obtaining the sampling points from the sorting result, the following steps are specifically realized:

The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, which can store various computer readable storage media.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.

The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be merged, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention.

While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A corneal topography reconstruction method, comprising:

acquiring an image to be reconstructed;

extracting a white ring effective outline from the segmentation result;

sequencing the white ring effective outlines to obtain a sequencing result;

acquiring sampling points from the sequencing result;

reconstructing a corneal topography by taking the sampling points as input quantities of reconstructed corneal physical values;

wherein the sorting the white ring effective outlines to obtain a sorting result comprises:

2. A corneal topography reconstruction method according to claim 1, wherein said segmentation model is obtained by training a convolutional neural network model using a Placido ring cornea image with a Placido black-and-white ring segmentation label as a sample set.

3. A corneal topography reconstruction method according to claim 2, wherein the segmentation model is obtained by training a convolutional neural network model using a Placido ring cornea image with a segmentation label of Placido black and white rings as a sample set, and includes:

performing data enhancement on the sample set to form a processed sample set;

4. A corneal topography reconstruction method according to claim 3, wherein said data enhancing said sample set to form a processed sample set comprises:

5. A corneal topography reconstruction method according to claim 1, wherein said extracting a white ring effective contour from said segmentation result comprises;

6. A corneal topography reconstruction method according to claim 1, wherein said sorting said white ring effective contours to obtain a sorted result comprises:

7. A corneal topography reconstruction method according to claim 6, wherein said obtaining sample points from said ordered result comprises:

8. A corneal topography reconstruction device, comprising:

the image acquisition unit is used for acquiring an image to be reconstructed;

the reconstruction unit is used for reconstructing a corneal topography map by taking the sampling points as input quantities of reconstructed corneal physical values;