CN116342636B - Eye anterior segment OCT image contour fitting method - Google Patents
Eye anterior segment OCT image contour fitting method Download PDFInfo
- Publication number
- CN116342636B CN116342636B CN202310580936.5A CN202310580936A CN116342636B CN 116342636 B CN116342636 B CN 116342636B CN 202310580936 A CN202310580936 A CN 202310580936A CN 116342636 B CN116342636 B CN 116342636B
- Authority
- CN
- China
- Prior art keywords
- cornea
- lens
- contour
- iris
- self
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 210000004087 cornea Anatomy 0.000 claims abstract description 209
- 210000000695 crystalline len Anatomy 0.000 claims abstract description 135
- 210000001508 eye Anatomy 0.000 claims description 93
- 239000002775 capsule Substances 0.000 claims description 54
- 210000001747 pupil Anatomy 0.000 claims description 51
- 210000000184 posterior capsule of the len Anatomy 0.000 claims description 36
- 210000002300 anterior capsule of the len Anatomy 0.000 claims description 27
- 238000000605 extraction Methods 0.000 claims description 25
- 238000003708 edge detection Methods 0.000 claims description 19
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 5
- 210000005252 bulbus oculi Anatomy 0.000 claims description 3
- 201000010099 disease Diseases 0.000 abstract description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 4
- 238000012014 optical coherence tomography Methods 0.000 description 118
- 239000012528 membrane Substances 0.000 description 17
- 230000003044 adaptive effect Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 10
- 210000001519 tissue Anatomy 0.000 description 5
- 230000007704 transition Effects 0.000 description 5
- 230000006978 adaptation Effects 0.000 description 4
- 238000003759 clinical diagnosis Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003325 tomography Methods 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 208000002177 Cataract Diseases 0.000 description 1
- 210000002294 anterior eye segment Anatomy 0.000 description 1
- 210000001742 aqueous humor Anatomy 0.000 description 1
- 230000001746 atrial effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011284 combination treatment Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003698 laser cutting Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000001491 myopia Diseases 0.000 description 1
- 230000004379 myopia Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/102—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for optical coherence tomography [OCT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10101—Optical tomography; Optical coherence tomography [OCT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Multimedia (AREA)
- Biophysics (AREA)
- Ophthalmology & Optometry (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method for fitting OCT image contours of anterior ocular segment, which comprises the following steps: extracting to obtain OCT images of the anterior ocular segment in the five characteristic areas, and obtaining edge contour data of the OCT images of the anterior ocular segment in the five characteristic areas; fitting to obtain a least square cubic polynomial fitting curve, and obtaining a three-point arc fitting curve through three-point arc fitting; combining the obtained least square cubic polynomial fitting curve and the three-point curve fitting curve to obtain four self-adaptive templates: adding lines to the four self-adaptive templates and filling to obtain a self-adaptive template for filling cornea and a self-adaptive template for filling crystalline lens; respectively extracting a cornea OCT image and a lens OCT image to obtain edge contour data of an OCT image of an anterior segment of an eye; and obtaining an edge contour fitting curve of the OCT image of the anterior ocular segment through piecewise fitting. The method and the device can improve the precision and the speed of the contour fitting of the OCT image of the anterior segment of the eye and realize the clinical precision and the real-time performance of the ophthalmic diseases.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an OCT image contour fitting method for anterior ocular segment.
Background
Optical tomography (optical coherence tomography, OCT) is widely used in the ophthalmic field. Based on the optical tomography two-dimensional image of the anterior ocular segment tissue, the depth parameters of the anterior ocular segment tissue are further measured by extracting the edge outline of the ocular tissue and fitting a curve, so that the method is not only beneficial to clinical diagnosis of ophthalmic diseases, such as three-dimensional reconstruction of the anterior ocular segment, measurement of cornea curvature, central cornea thickness, atrial angle and the like, but also greatly improves the precision and the speed of clinical operation treatment of the ophthalmic diseases, such as assisting doctor diagnosis, laser myopia correction, laser cataract operation and the like, providing the depth parameters to guide laser cutting depth and the like. Wherein, the contour fitting of anterior and posterior surfaces of cornea and anterior and posterior capsule membranes of crystalline lens of OCT image of anterior segment of eye is necessary precondition.
However, the existing anterior ocular segment OCT image contour fitting method has at least the following problems:
background noise interference (such as aqueous humor) of the OCT image of the anterior segment of the eye and low signal-to-noise ratio areas of the OCT image of the anterior segment of the eye, such as weak signals on two sides of the cornea and central oversaturation artifacts caused by a telecentric scanning mode, are not effectively processed. The existing method processes the whole image to determine the edge contour of the anterior segment of the eye, the processing speed is low, and the contour fitting precision is low due to low feature angular point extraction precision. Therefore, the accuracy and the rapidity of the subsequent measurement of the anterior ocular segment tissue depth parameters are affected, and the requirements of clinical accuracy and real-time performance cannot be met.
Disclosure of Invention
In view of the foregoing, it is necessary to provide an anterior ocular segment OCT image contour fitting method that can improve the accuracy and speed of anterior ocular segment OCT image contour fitting.
The invention provides a method for fitting OCT image contours of anterior ocular segments, which comprises the following steps: s1, selecting five characteristic areas based on the eyeball structure of a human eye, manufacturing five characteristic area extraction templates in an OCT image coordinate system of the anterior ocular segment to extract and obtain OCT images of the anterior ocular segment in the five characteristic areas, and obtaining edge contour data of the OCT images of the anterior ocular segment in the five characteristic areas through image preprocessing; s2, based on the obtained edge contour data of the OCT images of the anterior ocular segment in the five characteristic areas, obtaining a least square cubic polynomial fitting curve through least square cubic polynomial fitting, extracting the top points and the end points of the least square cubic polynomial fitting curve, and obtaining a three-point arc fitting curve through three-point arc fitting; s3, combining the obtained least square cubic polynomial fitting curve and the three-point arc fitting curve to obtain four self-adaptive templates: the method comprises the steps of adding lines to the four self-adaptive templates and filling the lines to obtain a cornea-filling self-adaptive template and a lens-filling self-adaptive template; s4, respectively extracting a cornea OCT image and a lens OCT image based on the obtained self-adaptive cornea filling template and self-adaptive lens filling template, and obtaining edge contour data of an OCT image of the anterior segment of the eye through image edge detection; s5, respectively extracting cornea front surface edge profile data, cornea rear surface edge profile data, lens front capsular bag edge profile data and lens rear capsular bag edge profile data based on the obtained cornea front surface self-adaptive template, cornea rear surface self-adaptive template, lens front capsular bag self-adaptive template and lens rear capsular bag self-adaptive template, and obtaining an edge profile fitting curve of an OCT image of an anterior ocular segment through segmentation fitting.
Specifically, the five feature regions include an eye white to iris region, an iris to pupil region, a pupil center region, a pupil to iris region, and an iris to eye white region.
Specifically, the step S1 further includes:
s12, converting the region ranges of the five characteristic regions into an OCT image pixel coordinate system, converting the scanning depth of an OCT system into the OCT image pixel coordinate system, and manufacturing the five characteristic region extraction templates under the OCT image pixel coordinate system; in the OCT image of the anterior ocular segment, based on the five characteristic areas, extracting templates, and performing image processing with the OCT image of the anterior ocular segment to obtain OCT images of the anterior ocular segment in the five characteristic areas;
step S13, performing image preprocessing on the OCT images of the anterior ocular segment in the five characteristic areas to obtain binarized images of the OCT images of the anterior ocular segment in the five characteristic areas; and carrying out contour extraction on the binarized images of the five characteristic areas to obtain the edge contour of the images in the five characteristic areas of the OCT image of the anterior segment of the eye.
Specifically, the image preprocessing comprises image enhancement, image convolution, binarization and contour extraction.
Specifically, the step S2 includes:
Step S21, extracting all contour points which form the anterior surface of the cornea in the five characteristic areas: the method comprises the steps of composing contour points of the front surface of the cornea in an area from the eye white to the iris, composing contour points of the front surface of the cornea in an area from the iris to the pupil, composing contour points of the front surface of the cornea in a central area of the pupil, composing contour points of the front surface of the cornea in an area from the pupil to the iris, composing contour points of the front surface of the cornea in an area from the iris to the eye white;
step S22, extracting all contour points which form the cornea back surface in the five characteristic areas: the method comprises the steps of composing contour points of the cornea back surface from the eye white to the iris, composing contour points of the cornea back surface from the iris to the pupil, composing contour points of the cornea back surface from the pupil center, composing contour points of the cornea back surface from the pupil to the iris, composing contour points of the cornea back surface from the iris to the eye white;
step S23, extracting all contour points which form the anterior capsule of the lens in the five characteristic areas: the method comprises the steps of composing contour points of a front capsule of a lens in an area from white to iris, composing contour points of the front capsule of the lens in an area from iris to pupil, composing contour points of the front capsule of the lens in a central area of pupil, composing contour points of the front capsule of the lens in an area from pupil to iris, composing contour points of the front capsule of the lens in an area from iris to white;
Step S24, extracting all contour points which form the posterior capsule of the lens in the five characteristic areas: the method comprises the steps of composing contour points of a lens posterior capsule in an area from eye white to iris, composing contour points of a lens posterior capsule in an area from iris to pupil, composing contour points of a lens posterior capsule in a central area of pupil, composing contour points of a lens posterior capsule in an area from pupil to iris, and composing contour points of a lens posterior capsule in an area from iris to eye white;
step S25, obtaining a least square cubic polynomial fitting curve of the contour of the front surface of the cornea in the five characteristic areas by a least square cubic polynomial fitting method based on all contour points forming the front surface of the cornea in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; based on the endpoints and the vertexes, selecting connected three points to perform arc fitting to obtain a three-point arc fitting curve of the cornea front surface profile;
step S26, obtaining a least square cubic polynomial fitting curve of the contour of the cornea back surface in the five characteristic areas by a least square cubic polynomial fitting method based on all contour points forming the cornea back surface in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; based on the endpoints and the vertexes, selecting connected three points to perform arc fitting to obtain a three-point arc fitting curve of the cornea back surface profile;
Step S27, obtaining a least square cubic polynomial fitting curve of the outline of the anterior capsule of the lens in the five characteristic areas by a least square cubic polynomial fitting method based on all outline points of the anterior capsule of the lens formed in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; based on the endpoints and the vertexes, selecting connected three points to perform arc fitting to obtain a three-point arc fitting curve of the anterior capsule contour of the crystalline lens;
step S28, obtaining a least square cubic polynomial fitting curve of the outline of the posterior capsule of the lens in the five characteristic areas by a least square cubic polynomial fitting method based on all outline points of the posterior capsule of the lens formed in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; and based on the endpoints and the vertexes, selecting the connected three points to perform arc fitting to obtain a three-point arc fitting curve of the posterior capsule contour of the crystalline lens.
Specifically, the step S3 includes:
step S31, combining the polynomial fitting curve of least square and three times of the outline of the front surface of the cornea in the five characteristic areas with the three-point curve fitting curve of the outline of the front surface of the cornea to obtain a cornea front surface self-adaptive template; combining the polynomial fitting curve of least square and cubic of the contour of the rear surface of the cornea in the five characteristic areas with the three-point curve fitting curve of the contour of the rear surface of the cornea to obtain a self-adaptive template of the rear surface of the cornea; combining the polynomial fitting curve of least square and cubic of the outline of the anterior capsule of the lens in the five characteristic areas with the three-point curve fitting curve of the outline of the anterior capsule of the lens to obtain a self-adaptive template of the anterior capsule of the lens; combining the polynomial fitting curve of least square and cubic of the outline of the posterior capsule of the lens in the five characteristic areas with the three-point curve fitting curve of the outline of the posterior capsule of the lens to obtain a self-adaptive template of the posterior capsule of the lens;
Step S32, combining the cornea front surface self-adaptive template and the cornea rear surface self-adaptive template, adding lines to form a closed image, and filling the outline to obtain a filled cornea self-adaptive template; and merging the anterior lens capsule self-adaptive template and the posterior lens capsule self-adaptive template, adding lines to form a closed image, and filling the outline to obtain the filling lens self-adaptive template.
Specifically, the step S4 includes:
s41, extracting a cornea OCT image based on the self-adaptive template of the filled cornea, and carrying out image edge detection on the cornea OCT image to obtain cornea edge contour data; extracting a lens OCT image based on the filling lens self-adaptive template, and carrying out image edge detection on the lens OCT image to obtain lens edge contour data;
and step S42, combining the cornea edge contour data and the crystalline lens edge contour data to obtain edge contour data of the OCT image of the anterior segment of the eye.
Specifically, the image edge detection includes: image enhancement, gaussian difference and morphological edge extraction.
Specifically, the step S5 includes:
step S51, extracting cornea front surface edge profile data based on a cornea front surface self-adaptive template, extracting cornea rear surface edge profile data based on a cornea rear surface self-adaptive template, extracting lens front capsular sac edge profile data based on a lens front capsular sac self-adaptive template, and extracting lens rear capsular sac edge profile data based on a lens rear capsular sac self-adaptive template;
Step S52, extracting outline data from the cornea front surface edge to the iris area and outline data from the iris to the eye area from the cornea front surface edge outline data, respectively performing least square polynomial fitting, and performing least square ellipse fitting on the rest cornea front surface edge outline data to finally obtain a fitting curve of the cornea front surface edge outline; extracting outline data from the cornea back surface edge outline data from the eye white to the iris area, performing least square polynomial fitting, extracting outline data from the iris to the eye white area, performing least square polynomial fitting, performing least square ellipse fitting on the rest cornea back surface edge outline data, and obtaining a fitting curve of the cornea back surface edge outline through segmentation fitting;
step S53, in the anterior capsular bag edge contour data of the crystalline lens, a least square ellipse fitting method is adopted to obtain a fitting curve of the final anterior capsular bag edge contour of the crystalline lens; in the edge profile data of the posterior capsule of the crystalline lens, a least square ellipse fitting method is adopted to obtain a fitting curve of the edge profile of the posterior capsule of the crystalline lens;
and S54, combining the fitting curve of the cornea front surface edge profile, the fitting curve of the cornea rear surface edge profile, the fitting curve of the lens front capsule and the fitting curve of the lens rear capsule to obtain a final fitting result of the eye front section OCT image edge profile.
The application includes anterior corneal surface edge profile data fitting, posterior corneal surface edge profile data fitting, anterior lens capsule edge profile data fitting, and posterior lens capsule edge profile data fitting. The accuracy of the contour fitting plays an important role in assisting a doctor in clinical diagnosis, operation and the like. The method comprises the steps of selecting five characteristic areas of an OCT image of a front eye section; performing image preprocessing on the OCT images of the anterior ocular segment in the five characteristic areas to obtain edge contour data of the OCT images of the anterior ocular segment in the five characteristic areas; performing least square cubic polynomial fitting, endpoint vertex extraction, three-point arc fitting and combination treatment on edge profile data to obtain a cornea front surface self-adaptive template, a cornea rear surface self-adaptive template, a lens front capsular membrane self-adaptive template and a lens rear capsular membrane self-adaptive template; obtaining a self-adaptive template for filling cornea and a self-adaptive template for filling crystalline lens by adding line filling treatment; performing edge detection on the OCT image of the anterior ocular segment in the self-adaptive template area of the filling cornea and the OCT image of the anterior ocular segment in the self-adaptive template area of the filling crystalline lens respectively to obtain edge contour data of the OCT image of the anterior ocular segment; and obtaining an edge contour fitting curve of the OCT image before eyes by carrying out edge contour data segmentation and segmentation fitting. The invention is based on the self-adaptive template, can improve the precision and the speed of the OCT image contour fitting of the anterior segment of the eye, and realizes the clinical precision and the real-time performance of the ophthalmic diseases.
Drawings
FIG. 1 is a flow chart of the anterior ocular segment OCT image contour fitting method of the present invention;
fig. 2 is a schematic diagram of marking five feature areas according to an OCT apparatus according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of image preprocessing according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a flow of image edge detection according to an embodiment of the present invention;
FIG. 5 is a flow chart of data fitting based on edge contour data points according to an embodiment of the present invention;
FIG. 6 is an OCT image of the anterior segment of the eye provided by an embodiment of the present invention;
fig. 7 is a schematic view of OCT images corresponding to the white-to-iris, pupil center, and iris-to-white area provided in an embodiment of the present invention;
fig. 8 is a schematic view of OCT images of corresponding iris-to-pupil, pupil-to-iris regions provided in an embodiment of the present invention;
FIG. 9 is a schematic diagram of an image processing result according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of a result of feature point extraction and least squares third order polynomial fitting provided in an embodiment of the present invention;
FIG. 11 is a schematic diagram of a least squares third order polynomial fitting result and a key first extraction result provided in an embodiment of the present invention;
FIG. 12 is a schematic diagram of the result of a combined least squares third order polynomial fit and a three-point arc fit provided by an embodiment of the present invention;
Fig. 13 is a schematic diagram of an OCT image-adaptive template for anterior segment of a closed eye according to an embodiment of the present invention;
FIG. 14 is a schematic view of a cornea anterior surface adaptation template provided in an embodiment of the present invention;
FIG. 15 is a schematic view of a cornea posterior surface adaptation template provided in an embodiment of the present invention;
FIG. 16 is a schematic view of an adaptive template for the anterior capsule of a lens according to an embodiment of the present invention;
FIG. 17 is a schematic view of a post-lens capsular bag adaptation template according to an embodiment of the present invention;
FIG. 18 is a schematic diagram of a filled cornea adaptive template provided by an embodiment of the present invention;
FIG. 19 is a schematic view of a filled lens adaptive template provided in an embodiment of the present invention;
FIG. 20 is a graph showing the results of limbus detection provided by an embodiment of the present invention;
FIG. 21 is a graph showing the results of lens edge detection according to an embodiment of the present invention;
fig. 22 is a schematic diagram of an edge detection result of an OCT image of the anterior segment of the eye according to an embodiment of the present invention;
FIG. 23 is a schematic view of corneal anterior surface edge profile data point information provided in an embodiment of the present invention;
FIG. 24 is a schematic representation of corneal posterior surface edge profile data point information provided in an embodiment of the present invention;
FIG. 25 is a schematic view of anterior lens capsule edge contour data point information provided in an embodiment of the present invention;
FIG. 26 is a schematic representation of post-lens capsular rim contour data point information provided in an embodiment of the present invention;
fig. 27 is a schematic diagram of an edge profile fitting result of an OCT image of the anterior segment of the eye according to an embodiment of the present invention.
Detailed Description
The invention will be described in further detail with reference to the accompanying drawings and specific examples.
Referring to fig. 1, a flowchart of the method for fitting OCT image contours of the anterior segment of the eye according to a preferred embodiment of the present invention is shown.
Step S1, acquiring edge contour data of OCT images of anterior ocular segment in five characteristic areas: five characteristic areas are selected based on the eyeball structure of the human eye, five characteristic area extraction templates are manufactured in an OCT image coordinate system of the anterior ocular segment to extract and obtain OCT images of the anterior ocular segment in the five characteristic areas, and edge contour data of the OCT images of the anterior ocular segment in the five characteristic areas are obtained through image preprocessing.
The method specifically comprises the following steps:
step S11, the five characteristic areas comprise an eye white-to-iris area, an iris-to-pupil area, a pupil center area, a pupil-to-iris area and an iris-to-eye white area, wherein the eye white-to-iris area is a transition area from eye white to iris, the eye white is contained in the left side of the iris, the iris is on the right side of the eye white, and the area range is 1mm; the iris-to-eye white area is a transition area from the iris to the eye white, the transition area comprises the iris and the eye white, the iris is positioned on the left side of the eye white, the eye white is positioned on the right side of the iris, and the area of the area is 1mm; the iris-to-pupil area is an iris-to-pupil transition area, which comprises the iris and the pupil, wherein the iris is positioned on the left side of the pupil, the pupil is positioned on the right side of the iris, and the area of the area is 1mm; the pupil-to-iris region is a pupil-to-iris transition region, which comprises the pupil and the iris, the pupil is positioned on the left side of the iris, the iris is positioned on the right side of the pupil, and the region range is 1mm; the pupil center region is a region within 1mm of the pupil.
S12, converting the region ranges of the five characteristic regions into an OCT image pixel coordinate system, converting the scanning depth of an OCT system into the OCT image pixel coordinate system, and manufacturing the five characteristic region extraction templates under the OCT image pixel coordinate system; in the anterior ocular segment OCT image, based on the five characteristic regions, extracting templates, and performing image processing with the anterior ocular segment OCT image to obtain anterior ocular segment OCT images in the five characteristic regions.
Step S13, performing image preprocessing on the OCT images of the anterior ocular segment in the five characteristic areas to obtain binarized images of the OCT images of the anterior ocular segment in the five characteristic areas; and carrying out contour extraction on the binarized images of the five characteristic areas to obtain the edge contour of the images in the five characteristic areas of the OCT image of the anterior segment of the eye.
It should be noted that, when the OCT apparatus adopts a telecentric scan mode for anterior segment tissue of the eye, signals on both sides of the cornea are weaker, and the iris-to-pupil area and the anterior segment OCT image of the pupil-to-iris area selected in this embodiment belong to both sides of the cornea, and when the image is preprocessed, an image enhancement operation is adopted, so that the brightness and contrast of the images of the iris-to-pupil area and the pupil-to-iris area are increased, and the brightness and contrast of the images of the white-to-iris area, the pupil center area and the iris-to-white area are reduced.
It should be noted that, since each feature region contains background noise, when contour extraction is performed, a contour of the background noise needs to be filtered, that is, the length and width of the contour-encased rectangle are set, and when the length and width of the contour-encased rectangle are greater than the set values, the contour is selected, otherwise, the contour is filtered.
The following description is made with reference to specific embodiments and accompanying drawings:
step S11, referring to FIG. 2, five characteristic areas of the OCT image of the anterior segment of the eye are selected, namely an eye white-to-iris area, an iris-to-pupil area, a pupil center area, a pupil-to-iris area and an iris-to-eye white area. In this embodiment, the OCT images of the anterior segment of the eye are shown in fig. 6, the OCT images of the anterior segment of the eye from the white to the iris region, the pupil center region, and the iris to the white region are shown in fig. 7, and the OCT images of the anterior segment of the eye from the iris to the pupil region and the pupil to the iris region are shown in fig. 8.
And S12, manufacturing five characteristic region extraction templates under an OCT image pixel coordinate system.
Step S13, an image preprocessing step is shown in FIG. 3, and comprises the steps of image enhancement, image convolution, step binarization, contour extraction and the like; considering that the OCT equipment adopts a telecentric scanning mode to cause weak signals on two sides of a cornea, for OCT images of the front eye section of an iris-to-pupil characteristic region and a pupil-to-iris characteristic region, the parameters of image enhancement are larger than those of OCT images of the front eye section of the white-to-iris characteristic region, a pupil center region and an iris-to-white region; the convolution kernel adopted by the image convolution is kernel= [ 010, 1, 5, 0, 1; the binarization adopts fixed threshold binarization; and in the contour extraction process, the corresponding contour with the contour circumscribed rectangle length and width smaller than the set value is filtered, so that the influence of OCT image background noise of anterior ocular segment in the characteristic region is reduced.
Image enhancement, image convolution, binarization and contour extraction are respectively carried out on the OCT images of the anterior ocular segment in the characteristic areas shown in fig. 7 and 8, so as to obtain edge contour data of the OCT images of the anterior ocular segment in the five characteristic areas, as shown in fig. 9.
Step S2, a least square cubic polynomial fitting curve and a three-point arc fitting curve are obtained: and (3) based on the edge contour data of the OCT images of the anterior ocular segment in the five characteristic areas obtained in the step (S1), obtaining a least square cubic polynomial fitting curve through least square cubic polynomial fitting, extracting the top points and the end points of the least square cubic polynomial fitting curve, and obtaining a three-point arc fitting curve through three-point arc fitting.
The method specifically comprises the following steps:
step S21, extracting all contour points which form the anterior surface of the cornea in the five characteristic areas: the method comprises the steps of composing contour points of the front surface of the cornea in the area from the eye white to the iris, composing contour points of the front surface of the cornea in the area from the iris to the pupil, composing contour points of the front surface of the cornea in the central area of the pupil, composing contour points of the front surface of the cornea in the area from the pupil to the iris, and composing contour points of the front surface of the cornea in the area from the iris to the eye white.
Step S22, extracting all contour points which form the cornea back surface in the five characteristic areas: the method comprises the steps of composing contour points of the cornea back surface from the eye white to the iris, composing contour points of the cornea back surface from the iris to the pupil, composing contour points of the cornea back surface from the pupil center, composing contour points of the cornea back surface from the pupil to the iris, composing contour points of the cornea back surface from the iris to the eye white.
Step S23, extracting all contour points which form the anterior capsule of the lens in the five characteristic areas: the method comprises the steps of composing contour points of the anterior capsule of the lens in the region from the white of the eye to the iris, composing contour points of the anterior capsule of the lens in the region from the iris to the pupil, composing contour points of the anterior capsule of the lens in the central region of the pupil, composing contour points of the anterior capsule of the lens in the region from the pupil to the iris, and composing contour points of the anterior capsule of the lens in the region from the iris to the white of the eye.
Step S24, extracting all contour points which form the posterior capsule of the lens in the five characteristic areas: the method comprises the steps of composing contour points of the back capsule membrane of the crystalline lens in the area from the white of the eye to the iris, composing contour points of the back capsule membrane of the crystalline lens in the area from the iris to the pupil, composing contour points of the back capsule membrane of the crystalline lens in the central area of the pupil, composing contour points of the back capsule membrane of the crystalline lens in the area from the pupil to the iris, and composing contour points of the back capsule membrane of the crystalline lens in the area from the iris to the white of the eye.
Step S25, obtaining a least square cubic polynomial fitting curve of the contour of the front surface of the cornea in the five characteristic areas by a least square cubic polynomial fitting method based on all contour points forming the front surface of the cornea in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; and selecting the connected three points to perform arc fitting based on the endpoints and the vertexes, and obtaining a three-point arc fitting curve of the cornea front surface profile.
Step S26, obtaining a least square cubic polynomial fitting curve of the contour of the cornea back surface in the five characteristic areas by a least square cubic polynomial fitting method based on all contour points forming the cornea back surface in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; and selecting the connected three points to perform arc fitting based on the endpoints and the vertexes, and obtaining a three-point arc fitting curve of the cornea back surface profile.
Step S27, obtaining a least square cubic polynomial fitting curve of the outline of the anterior capsule of the lens in the five characteristic areas by a least square cubic polynomial fitting method based on all outline points of the anterior capsule of the lens formed in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; and selecting three connected points to perform arc fitting based on the endpoints and the vertexes to obtain a three-point arc fitting curve of the anterior capsule contour of the crystalline lens.
Step S28, obtaining a least square cubic polynomial fitting curve of the outline of the posterior capsule of the lens in the five characteristic areas by a least square cubic polynomial fitting method based on all outline points of the posterior capsule of the lens formed in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; and based on the endpoints and the vertexes, selecting the connected three points to perform arc fitting to obtain a three-point arc fitting curve of the posterior capsule contour of the crystalline lens.
It should be noted that, the edge profile data of the OCT image of the anterior segment of the eye in the five feature areas has interference data, so that errors exist in the extracted end points and vertices, and the embodiment extracts the end points and vertices of the least squares fit curve of the five feature areas based on the least squares polynomial fit result in the five feature areas, so as to avoid the errors.
The following description is made with reference to specific embodiments and accompanying drawings:
step S21, step S22, step S23, step S24, extracting an end point of an eye white to an edge contour of an OCT image of an anterior ocular segment in an iris region, an end point of an OCT image of an anterior ocular segment in an iris to pupil region, an end point of an OCT image of an anterior ocular segment in a pupil center region, an end point of an OCT image of an anterior ocular segment in an iris to an eye white region, based on edge contour data of OCT images of anterior ocular segments in five feature regions shown in fig. 9, as shown in fig. 10; based on the end points, all contour points in five characteristic areas, which form the anterior surface of the cornea, all contour points in five characteristic areas, which form the posterior surface of the cornea, all contour points in five characteristic areas, which form the anterior capsule of the lens, and all contour points in five characteristic areas, which form the posterior capsule of the lens, are extracted.
Step S25, step S26, step S27, step S28, fitting by using a least square cubic polynomial based on all contour points forming the anterior surface of the cornea in five characteristic areas, all contour points forming the posterior surface of the cornea in five characteristic areas, all contour points forming the anterior capsule of the lens in five characteristic areas, and all contour points forming the posterior capsule of the lens in five characteristic areas, respectively, to obtain a least square cubic polynomial fit curve of the contour of the anterior surface of the cornea in five characteristic areas, a least square cubic polynomial fit curve of the contour of the posterior surface of the cornea in five characteristic areas, a least square cubic polynomial fit curve of the contour of the anterior capsule of the lens in five characteristic areas, and a least square cubic polynomial fit curve of the contour of the posterior capsule of the lens in five characteristic areas, and extracting end points and vertexes as shown in FIG. 11; selecting the cornea front surface profile data from the cornea white to the right upper end point of the iris region, the cornea upper surface fitting curve vertex of the pupil center region and the iris to the left upper end point of the cornea white region, and performing three-point arc line fitting, wherein the three-point arc line fitting result of the cornea front surface profile is shown in fig. 12; selecting cornea back surface eye white to iris region cornea back surface end point, pupil center region cornea back surface fitting curve top point, iris to eye white region cornea back surface end point, performing three-point arc line fitting, and cornea back surface contour three-point arc line fitting result is shown in figure 12; selecting the front lens capsule data, performing three-point arc line fitting from the iris to the front lens capsule end point of the pupil area and the two end points of the front lens capsule fitting curve of the pupil center area, selecting the two end points of the front lens capsule fitting curve of the pupil center area and the front lens capsule end point of the pupil area, performing three-point arc line fitting, and combining to obtain a front lens capsule three-point arc line fitting result shown in fig. 12; and in the data of the posterior capsule of the lens, three-point arc line fitting is carried out from the iris to the end point of the posterior capsule of the lens in the pupil area and from the iris to the end point of the fitting curve of the posterior capsule of the lens in the pupil center area, three-point arc line fitting is carried out from the pupil to the end point of the lens of the posterior capsule of the lens in the iris area, and the three-point arc line fitting results of the anterior capsule of the lens are shown in figure 12 after combining.
Step S3, preparing an adaptive template: and (2) combining the least square cubic polynomial fitting curve and the three-point arc fitting curve obtained in the step (S2) to obtain a cornea front surface self-adaptive template, a cornea rear surface self-adaptive template, a lens anterior capsule self-adaptive template and a lens rear capsule self-adaptive template, adding lines to the four self-adaptive templates, and filling the lines to obtain a cornea filling self-adaptive template and a lens filling self-adaptive template.
The method specifically comprises the following steps:
step S31, combining the polynomial fitting curve of least square and three times of the outline of the front surface of the cornea in the five characteristic areas with the three-point curve fitting curve of the outline of the front surface of the cornea to obtain a cornea front surface self-adaptive template; combining the polynomial fitting curve of least square and cubic of the contour of the rear surface of the cornea in the five characteristic areas with the three-point curve fitting curve of the contour of the rear surface of the cornea to obtain a self-adaptive template of the rear surface of the cornea; combining the polynomial fitting curve of least square and cubic of the outline of the anterior capsule of the lens in the five characteristic areas with the three-point curve fitting curve of the outline of the anterior capsule of the lens to obtain a self-adaptive template of the anterior capsule of the lens; and combining the polynomial fitting curve of least square and three times of the outline of the posterior capsule of the lens in the five characteristic areas with the three-point arc fitting curve of the outline of the posterior capsule of the lens to obtain the self-adaptive template of the posterior capsule of the lens.
It should be noted that, since the three-point curve fitting curve of the anterior ocular segment OCT image edge contour cannot be accurately matched with the anterior ocular segment OCT image edge contour, this error can be compensated by combining the least square third order polynomial fitting curve in the five feature regions and the three-point curve fitting curve of the anterior ocular segment OCT image edge contour.
Step S32, combining the cornea front surface self-adaptive template and the cornea rear surface self-adaptive template, adding lines to form a closed image, and filling the outline to obtain a filled cornea self-adaptive template; and merging the anterior lens capsule self-adaptive template and the posterior lens capsule self-adaptive template, adding lines to form a closed image, and filling the outline to obtain the filling lens self-adaptive template.
The following description is made with reference to specific embodiments and accompanying drawings:
step S31, combining the least squares fitting result shown in fig. 11 with the three-point arc fitting result of fig. 12 to obtain a cornea front surface adaptive template shown in fig. 14, a cornea rear surface adaptive template shown in fig. 15, a lens anterior capsule adaptive template shown in fig. 16, and a lens posterior capsule adaptive template shown in fig. 17.
Step S32, obtaining a closed eye anterior segment self-adaptive template by adding lines, wherein the closed eye anterior segment self-adaptive template is shown in FIG. 13; contour filling is performed to obtain a filled cornea adaptive template as shown in fig. 18, and contour filling is performed to obtain a filled lens adaptive template as shown in fig. 19.
Step S4, acquiring edge contour data of the OCT image of the anterior segment of the eye: and respectively extracting a cornea OCT image and a lens OCT image based on the obtained cornea filling self-adaptive template and lens filling self-adaptive template, and obtaining edge contour data of the OCT image of the anterior segment of the eye through image edge detection. The method specifically comprises the following steps:
s41, extracting a cornea OCT image based on the self-adaptive template of the filled cornea, and carrying out image edge detection on the cornea OCT image to obtain cornea edge contour data; and extracting a lens OCT image based on the filling lens self-adaptive template, and carrying out image edge detection on the lens OCT image to obtain lens edge contour data.
And step S42, combining the cornea edge contour data and the crystalline lens edge contour data to obtain edge contour data of the OCT image of the anterior segment of the eye.
It should be noted that, image preprocessing is performed on the OCT images of the anterior ocular segment in the five feature regions, and image edge detection is performed on the adaptive template region of the OCT images of the anterior ocular segment, so that edge profile data can be obtained; however, the edge contour data points obtained by adopting image edge detection are more accurate, on one hand, most of background noise is filtered out due to the adoption of the self-adaptive cornea filling template and the self-adaptive lens filling template obtained in the step S3; on the other hand, the image edge detection is higher than the contour data quality obtained by the image preprocessing.
The following description is made with reference to specific embodiments and accompanying drawings:
step S41, an image edge detection flow chart comprises image enhancement, gaussian difference and morphological edge extraction as shown in FIG. 4; extracting a cornea OCT image from the anterior ocular segment OCT image shown in fig. 6 by using the filled cornea self-adaptive template shown in fig. 18; extracting a lens OCT image using the stuffed lens adaptive template shown in fig. 19; performing image enhancement, gaussian difference and morphological edge extraction on the cornea OCT image to obtain edge contour data of the cornea OCT image as shown in figure 20; image enhancement, gaussian difference and morphological edge extraction are carried out on the OCT image of the lens, and edge data of the OCT image of the lens are obtained as shown in fig. 21.
Step S42, merging the edge profile data of the cornea OCT image shown in fig. 20 with the edge profile data of the lens OCT image shown in fig. 21 to obtain edge data of the anterior ocular segment OCT image is shown in fig. 22.
Step S5, obtaining an edge contour fitting curve of the anterior ocular segment OCT image (please refer to fig. 5): and respectively extracting cornea front surface edge profile data, cornea rear surface edge profile data, lens front capsular bag edge profile data and lens rear capsular bag edge profile data based on the obtained cornea front surface self-adaptive template, cornea rear surface self-adaptive template, lens front capsular bag self-adaptive template and lens rear capsular bag self-adaptive template, and obtaining an edge profile fitting curve of an OCT image of the anterior segment of the eye through piecewise fitting. The method specifically comprises the following steps:
Step S51, in the anterior ocular segment OCT image edge profile data: the method comprises the steps of extracting cornea front surface edge profile data based on a cornea front surface self-adaptive template, extracting cornea rear surface edge profile data based on a cornea rear surface self-adaptive template, extracting lens front capsular membrane edge profile data based on a lens front capsular membrane self-adaptive template, and extracting lens rear capsular membrane edge profile data based on a lens rear capsular membrane self-adaptive template.
The cornea front surface edge self-adaptive template, the cornea rear surface edge self-adaptive template, the lens front capsular membrane edge self-adaptive template and the lens rear capsular membrane edge self-adaptive template are adopted, so that the edge data of the OCT image of the anterior segment of the eye is segmented, and cornea front surface edge profile data, cornea rear surface edge profile data, lens front capsular membrane edge profile data and lens rear capsular membrane edge profile data are obtained.
Step S52, extracting outline data from the cornea front surface edge outline data from the eye white to the iris area and outline data from the iris to the eye white area, respectively performing least square polynomial fitting, and performing least square ellipse fitting on the rest cornea front surface edge outline data to finally obtain a fitting curve of the cornea front surface edge outline; and extracting outline data from the cornea back surface edge outline data from the eye white to the iris area, performing least square polynomial fitting, extracting outline data from the iris to the eye white area, performing least square polynomial fitting, performing least square ellipse fitting on the rest cornea back surface edge outline data, and obtaining a fitting curve of the cornea back surface edge outline through the piecewise fitting.
Step S53, in the anterior capsular bag edge contour data of the crystalline lens, a least square ellipse fitting method is adopted to obtain a fitting curve of the final anterior capsular bag edge contour of the crystalline lens; and in the post-lens capsular rim contour data, a least square ellipse fitting method is adopted to obtain a final fitting curve of the post-lens capsular rim contour.
And S54, combining the fitting curve of the cornea front surface edge profile, the fitting curve of the cornea rear surface edge profile, the fitting curve of the lens front capsule and the fitting curve of the lens rear capsule to obtain a final fitting result of the eye front section OCT image edge profile.
On one hand, the edge data precision of the OCT image of the anterior ocular segment extracted by the method is high, on the other hand, the edge contour central area of the anterior and posterior surface of the cornea and the edge contour of the anterior and posterior capsule membranes of the crystalline lens are approximately circular, and the precision of a fitting curve obtained by least square ellipse fitting is high; in addition, the precision of the obtained cornea front and back surface fitting curve is high by carrying out piecewise least square cubic polynomial fitting on the cornea front and back surface edge profile data.
The following description is made with reference to specific embodiments and accompanying drawings:
Step S51, extracting the edge profile data of the anterior cornea surface by using the adaptive template of the anterior cornea surface shown in FIG. 14 based on the edge data of the OCT image of the anterior eye segment shown in FIG. 22, as shown in FIG. 23; extracting the corneal posterior surface edge profile data using the corneal posterior surface adaptive template of fig. 15, as shown in fig. 24; extracting the anterior lens capsule edge profile data information using the anterior lens capsule adaptive template shown in fig. 16 as shown in fig. 25; the post-lens capsular bag edge contour data information is extracted using the post-lens capsular bag adaptation template shown in fig. 17 as shown in fig. 26.
Step S52, dividing the cornea front surface edge profile data shown in fig. 23 into 3 sections, wherein the first section is an edge profile data point covered by an eye white to iris region, the third section is an edge profile data point covered by an iris to eye white region, the rest data points are second section profile data, the profile data in the second section is fitted by a least square circle, the profile data in the first section and the third section are fitted by a least square cubic polynomial method, and the cornea front surface edge profile fitting result is shown in fig. 27; the corneal posterior surface edge profile data information shown in fig. 24 was divided into 3 segments, and the second segment was fitted by the least squares circle method, and the profile data in the first and third segments was fitted by the least squares third order polynomial method, as described above, and the result of the corneal posterior surface edge profile fitting was shown in fig. 27.
Step S53, fitting the anterior capsular rim contour data of the lens shown in fig. 25 by using a least square circle, obtaining an anterior capsular rim contour fitting curve of the lens shown in fig. 27, and fitting the anterior capsular rim contour data of the lens shown in fig. 26 by using a least square circle, obtaining a posterior capsular rim contour fitting curve of the lens shown in fig. 27.
Step S54, merging the cornea front surface edge profile fitting curve, the cornea rear surface edge profile fitting curve, the lens front capsular bag edge profile fitting curve and the lens rear capsular bag edge profile fitting curve to obtain an edge profile fitting curve of the OCT image of the anterior segment of the eye, as shown in fig. 27.
While the invention has been described with reference to the presently preferred embodiments, it will be understood by those skilled in the art that the foregoing is by way of illustration and not of limitation, and that any modifications, equivalents, variations and the like which fall within the spirit and scope of the principles of the invention are intended to be included within the scope of the appended claims.
Claims (6)
1. An eye anterior segment OCT image contour fitting method is characterized by comprising the following steps:
S1, selecting five characteristic areas based on the eyeball structure of a human eye, manufacturing five characteristic area extraction templates in an OCT image coordinate system of the anterior ocular segment to extract and obtain OCT images of the anterior ocular segment in the five characteristic areas, and obtaining edge contour data of the OCT images of the anterior ocular segment in the five characteristic areas through image preprocessing;
s2, based on the obtained edge contour data of the OCT images of the anterior ocular segment in the five characteristic areas, obtaining a least square cubic polynomial fitting curve through least square cubic polynomial fitting, extracting the top points and the end points of the least square cubic polynomial fitting curve, and obtaining a three-point arc fitting curve through three-point arc fitting;
s3, combining the obtained least square cubic polynomial fitting curve and the three-point arc fitting curve to obtain four self-adaptive templates: the method comprises the steps of adding lines to the four self-adaptive templates and filling the lines to obtain a cornea-filling self-adaptive template and a lens-filling self-adaptive template;
s4, respectively extracting a cornea OCT image and a lens OCT image based on the obtained self-adaptive cornea filling template and self-adaptive lens filling template, and obtaining edge contour data of an OCT image of the anterior segment of the eye through image edge detection;
S5, respectively extracting cornea front surface edge profile data, cornea rear surface edge profile data, lens front capsular bag edge profile data and lens rear capsular bag edge profile data based on the obtained cornea front surface self-adaptive template, cornea rear surface self-adaptive template, lens front capsular bag self-adaptive template and lens rear capsular bag self-adaptive template, and obtaining an edge profile fitting curve of an OCT image of an anterior ocular segment through segmentation fitting; wherein:
the five feature areas include an eye white to iris area, an iris to pupil area, a pupil center area, a pupil to iris area, and an iris to eye white area;
the step S2 includes:
step S21, extracting all contour points which form the anterior surface of the cornea in the five characteristic areas: the method comprises the steps of composing contour points of the front surface of the cornea in an area from the eye white to the iris, composing contour points of the front surface of the cornea in an area from the iris to the pupil, composing contour points of the front surface of the cornea in a central area of the pupil, composing contour points of the front surface of the cornea in an area from the pupil to the iris, composing contour points of the front surface of the cornea in an area from the iris to the eye white;
step S22, extracting all contour points which form the cornea back surface in the five characteristic areas: the method comprises the steps of composing contour points of the cornea back surface from the eye white to the iris, composing contour points of the cornea back surface from the iris to the pupil, composing contour points of the cornea back surface from the pupil center, composing contour points of the cornea back surface from the pupil to the iris, composing contour points of the cornea back surface from the iris to the eye white;
Step S23, extracting all contour points which form the anterior capsule of the lens in the five characteristic areas: the method comprises the steps of composing contour points of a front capsule of a lens in an area from white to iris, composing contour points of the front capsule of the lens in an area from iris to pupil, composing contour points of the front capsule of the lens in a central area of pupil, composing contour points of the front capsule of the lens in an area from pupil to iris, composing contour points of the front capsule of the lens in an area from iris to white;
step S24, extracting all contour points which form the posterior capsule of the lens in the five characteristic areas: the method comprises the steps of composing contour points of a lens posterior capsule in an area from eye white to iris, composing contour points of a lens posterior capsule in an area from iris to pupil, composing contour points of a lens posterior capsule in a central area of pupil, composing contour points of a lens posterior capsule in an area from pupil to iris, and composing contour points of a lens posterior capsule in an area from iris to eye white;
step S25, obtaining a least square cubic polynomial fitting curve of the contour of the front surface of the cornea in the five characteristic areas by a least square cubic polynomial fitting method based on all contour points forming the front surface of the cornea in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; based on the endpoints and the vertexes, selecting connected three points to perform arc fitting to obtain a three-point arc fitting curve of the cornea front surface profile;
Step S26, obtaining a least square cubic polynomial fitting curve of the contour of the cornea back surface in the five characteristic areas by a least square cubic polynomial fitting method based on all contour points forming the cornea back surface in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; based on the endpoints and the vertexes, selecting connected three points to perform arc fitting to obtain a three-point arc fitting curve of the cornea back surface profile;
step S27, obtaining a least square cubic polynomial fitting curve of the outline of the anterior capsule of the lens in the five characteristic areas by a least square cubic polynomial fitting method based on all outline points of the anterior capsule of the lens formed in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; based on the endpoints and the vertexes, selecting connected three points to perform arc fitting to obtain a three-point arc fitting curve of the anterior capsule contour of the crystalline lens;
step S28, obtaining a least square cubic polynomial fitting curve of the outline of the posterior capsule of the lens in the five characteristic areas by a least square cubic polynomial fitting method based on all outline points of the posterior capsule of the lens formed in the five characteristic areas; respectively extracting the endpoints and the vertexes of the polynomial fitting curve of the least square of the five characteristic areas; based on the endpoints and the vertexes, selecting three connected points to perform arc fitting to obtain a three-point arc fitting curve of the posterior capsule contour of the crystalline lens;
The step S3 includes:
step S31, combining the polynomial fitting curve of least square and three times of the outline of the front surface of the cornea in the five characteristic areas with the three-point curve fitting curve of the outline of the front surface of the cornea to obtain a cornea front surface self-adaptive template; combining the polynomial fitting curve of least square and cubic of the contour of the rear surface of the cornea in the five characteristic areas with the three-point curve fitting curve of the contour of the rear surface of the cornea to obtain a self-adaptive template of the rear surface of the cornea; combining the polynomial fitting curve of least square and cubic of the outline of the anterior capsule of the lens in the five characteristic areas with the three-point curve fitting curve of the outline of the anterior capsule of the lens to obtain a self-adaptive template of the anterior capsule of the lens; combining the polynomial fitting curve of least square and cubic of the outline of the posterior capsule of the lens in the five characteristic areas with the three-point curve fitting curve of the outline of the posterior capsule of the lens to obtain a self-adaptive template of the posterior capsule of the lens;
step S32, combining the cornea front surface self-adaptive template and the cornea rear surface self-adaptive template, adding lines to form a closed image, and filling the outline to obtain a filled cornea self-adaptive template; and merging the anterior lens capsule self-adaptive template and the posterior lens capsule self-adaptive template, adding lines to form a closed image, and filling the outline to obtain the filling lens self-adaptive template.
2. The method of claim 1, wherein said step S1 further comprises:
s12, converting the region ranges of the five characteristic regions into an OCT image pixel coordinate system, converting the scanning depth of an OCT system into the OCT image pixel coordinate system, and manufacturing the five characteristic region extraction templates under the OCT image pixel coordinate system; in the OCT image of the anterior ocular segment, based on the five characteristic areas, extracting templates, and performing image processing with the OCT image of the anterior ocular segment to obtain OCT images of the anterior ocular segment in the five characteristic areas;
step S13, performing image preprocessing on the OCT images of the anterior ocular segment in the five characteristic areas to obtain binarized images of the OCT images of the anterior ocular segment in the five characteristic areas; and carrying out contour extraction on the binarized images of the five characteristic areas to obtain the edge contour of the images in the five characteristic areas of the OCT image of the anterior segment of the eye.
3. The method of claim 2, wherein the image preprocessing comprises performing image enhancement, image convolution, binarization, and contour extraction.
4. A method as claimed in claim 3, wherein said step S4 comprises:
s41, extracting a cornea OCT image based on the self-adaptive template of the filled cornea, and carrying out image edge detection on the cornea OCT image to obtain cornea edge contour data; extracting a lens OCT image based on the filling lens self-adaptive template, and carrying out image edge detection on the lens OCT image to obtain lens edge contour data;
And step S42, combining the cornea edge contour data and the crystalline lens edge contour data to obtain edge contour data of the OCT image of the anterior segment of the eye.
5. The method of claim 4, wherein the image edge detection comprises: image enhancement, gaussian difference and morphological edge extraction.
6. The method of claim 5, wherein said step S5 comprises:
step S51, extracting cornea front surface edge profile data based on a cornea front surface self-adaptive template, extracting cornea rear surface edge profile data based on a cornea rear surface self-adaptive template, extracting lens front capsular sac edge profile data based on a lens front capsular sac self-adaptive template, and extracting lens rear capsular sac edge profile data based on a lens rear capsular sac self-adaptive template;
step S52, extracting outline data from the cornea front surface edge to the iris area and outline data from the iris to the eye area from the cornea front surface edge outline data, respectively performing least square polynomial fitting, and performing least square ellipse fitting on the rest cornea front surface edge outline data to finally obtain a fitting curve of the cornea front surface edge outline; extracting outline data from the cornea back surface edge outline data from the eye white to the iris area, performing least square polynomial fitting, extracting outline data from the iris to the eye white area, performing least square polynomial fitting, performing least square ellipse fitting on the rest cornea back surface edge outline data, and obtaining a fitting curve of the cornea back surface edge outline through segmentation fitting;
Step S53, in the anterior capsular bag edge contour data of the crystalline lens, a least square ellipse fitting method is adopted to obtain a fitting curve of the final anterior capsular bag edge contour of the crystalline lens; in the edge profile data of the posterior capsule of the crystalline lens, a least square ellipse fitting method is adopted to obtain a fitting curve of the edge profile of the posterior capsule of the crystalline lens;
and S54, combining the fitting curve of the cornea front surface edge profile, the fitting curve of the cornea rear surface edge profile, the fitting curve of the lens front capsule and the fitting curve of the lens rear capsule to obtain a final fitting result of the eye front section OCT image edge profile.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310580936.5A CN116342636B (en) | 2023-05-23 | 2023-05-23 | Eye anterior segment OCT image contour fitting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310580936.5A CN116342636B (en) | 2023-05-23 | 2023-05-23 | Eye anterior segment OCT image contour fitting method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116342636A CN116342636A (en) | 2023-06-27 |
| CN116342636B true CN116342636B (en) | 2023-12-29 |
Family
ID=86880688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310580936.5A Active CN116342636B (en) | 2023-05-23 | 2023-05-23 | Eye anterior segment OCT image contour fitting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116342636B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116777794B (en) * | 2023-08-17 | 2023-11-03 | 简阳市人民医院 | Cornea foreign body image processing method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102136135A (en) * | 2011-03-16 | 2011-07-27 | 清华大学 | Method for extracting inner outline of cornea from optical coherence tomography image of anterior segment of eye and method for extracting inner outline of anterior chamber from optical coherence tomography image of anterior segment of eye |
| CN108814544A (en) * | 2018-04-25 | 2018-11-16 | 天津市索维电子技术有限公司 | A kind of anterior ocular segment morphological analysis method |
| CN110110761A (en) * | 2019-04-18 | 2019-08-09 | 温州医科大学 | The image characteristic extracting method of anterior ocular segment faultage image based on machine vision |
| CN111260610A (en) * | 2020-01-08 | 2020-06-09 | 上海美沃精密仪器股份有限公司 | Anterior segment state characterization method and system based on room angle open distance curve |
-
2023
- 2023-05-23 CN CN202310580936.5A patent/CN116342636B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102136135A (en) * | 2011-03-16 | 2011-07-27 | 清华大学 | Method for extracting inner outline of cornea from optical coherence tomography image of anterior segment of eye and method for extracting inner outline of anterior chamber from optical coherence tomography image of anterior segment of eye |
| CN108814544A (en) * | 2018-04-25 | 2018-11-16 | 天津市索维电子技术有限公司 | A kind of anterior ocular segment morphological analysis method |
| CN110110761A (en) * | 2019-04-18 | 2019-08-09 | 温州医科大学 | The image characteristic extracting method of anterior ocular segment faultage image based on machine vision |
| CN111260610A (en) * | 2020-01-08 | 2020-06-09 | 上海美沃精密仪器股份有限公司 | Anterior segment state characterization method and system based on room angle open distance curve |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116342636A (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1516156B1 (en) | Tracking torsional eye orientation and position | |
| EP2477587B1 (en) | Registration of corneal flap with ophthalmic measurement and/or treatment data for lasik and other procedures | |
| Tian et al. | Automatic anterior chamber angle assessment for HD-OCT images | |
| CN116342636B (en) | Eye anterior segment OCT image contour fitting method | |
| CN110400289A (en) | Eye fundus image recognition methods, device, equipment and storage medium | |
| US9833136B2 (en) | Systems and methods for ocular anterior segment tracking, alignment, and dewarping using optical coherence tomography | |
| CN108257126B (en) | Blood vessel detection and registration method, equipment and application of three-dimensional retina OCT image | |
| CN111616800B (en) | Ophthalmic surgery navigation system | |
| CN110210357B (en) | Ptosis image measuring method based on static photo face recognition | |
| CN113643353B (en) | Measurement method for enhancing resolution of vascular caliber of fundus image | |
| CN111583248B (en) | Processing method based on eye ultrasonic image | |
| CN113940812A (en) | Cornea center positioning method for excimer laser cornea refractive surgery | |
| CN111861977A (en) | Feature extraction method of anterior segment tomogram based on machine vision | |
| CN116030042A (en) | Diagnostic device, method, equipment and storage medium for doctor's diagnosis | |
| CN113012151B (en) | OCT (optical coherence tomography) image correction method and system for SS-OCT operation navigation system | |
| CN116309661B (en) | Method for extracting OCT (optical coherence tomography) image contour of anterior segment of eye | |
| WO2015188279A1 (en) | Non-invasive measurement of choroidal volume change and ocular rigidity through oct imaging | |
| US20210315454A1 (en) | Morphology determining method and morphology determining system of corneal topography | |
| CN114373216A (en) | Eye movement tracking method, device, equipment and storage medium for anterior segment OCTA | |
| CN116309594B (en) | OCT image processing method for anterior ocular segment | |
| CN112155554A (en) | Method, device and equipment for determining individual development age based on cranium surface morphological development characteristics of children and teenagers | |
| Syga et al. | A fully automated 3D in-vivo delineation and shape parameterization of the human lamina cribrosa in optical coherence tomography | |
| Xu et al. | Retinal vessel segmentation on SLO image | |
| Santhakumar et al. | A fast algorithm for optic disc segmentation in fundus images | |
| CN108231165A (en) | A kind of auxiliary system of eye disease diagnosis |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |