CN116309594B - OCT image processing method for anterior ocular segment - Google Patents

OCT image processing method for anterior ocular segment Download PDF

Info

Publication number
CN116309594B
CN116309594B CN202310580898.3A CN202310580898A CN116309594B CN 116309594 B CN116309594 B CN 116309594B CN 202310580898 A CN202310580898 A CN 202310580898A CN 116309594 B CN116309594 B CN 116309594B
Authority
CN
China
Prior art keywords
characteristic
image
oct image
angular point
point
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
Application number
CN202310580898.3A
Other languages
Chinese (zh)
Other versions
CN116309594A (en
Inventor
周辉
王月虹
韩寒
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Medical Research And Development Co ltd
Original Assignee
Guangdong Medical Research And Development Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Medical Research And Development Co ltd filed Critical Guangdong Medical Research And Development Co ltd
Priority to CN202310580898.3A priority Critical patent/CN116309594B/en
Publication of CN116309594A publication Critical patent/CN116309594A/en
Application granted granted Critical
Publication of CN116309594B publication Critical patent/CN116309594B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • 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
    • G06T7/10—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)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Multimedia (AREA)
  • Biophysics (AREA)
  • Ophthalmology & Optometry (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Eye Examination Apparatus (AREA)
  • Image Analysis (AREA)

Abstract

The application relates to a method for processing OCT images of anterior ocular segments, which comprises the following steps: manufacturing a self-adaptive template to obtain OCT images of anterior ocular segment in three characteristic areas; obtaining the edge contour data of the OCT image of the anterior ocular segment in three characteristic areas according to the obtained OCT image of the anterior ocular segment; extracting edge contour data of OCT images of the anterior ocular segment in the three obtained characteristic areas to obtain first characteristic angular points of the OCT images of the anterior ocular segment; extracting an OCT image of the anterior segment of the eye in the first characteristic angular point area based on the acquired first characteristic angular point, and extracting a second characteristic angular point through an edge detection algorithm; and selecting a third characteristic angular point of the OCT image of the anterior segment of the eye based on the first characteristic angular point and the second characteristic angular point, and calculating according to the third characteristic angular point to obtain the inclination angle and the inclination axis of the OCT image of the anterior segment of the eye. The application can improve the calculation precision of the inclination angle and the measurement precision of the anterior ocular segment tissue, and realize the clinical precision and real-time performance of the ophthalmic diseases.

Description

OCT image processing method for anterior ocular segment
Technical Field
The application relates to the technical field of image processing, in particular to an OCT image processing method for anterior ocular segment.
Background
Optical tomography (optical coherence tomography, OCT) is widely used in the ophthalmic field. Based on the optical tomographic image of the anterior ocular segment tissue, the angle of inclination is calculated by extracting the outline feature corner of the ocular tissue edge, and the corneal curvature, the central corneal thickness and the like are further measured, thereby playing an important role in clinical diagnosis of ophthalmic diseases. Wherein, the extraction of characteristic angular points and the calculation of the inclination angle are necessary preconditions.
The prior art processes the background noise interference (such as aqueous humor and the like) of the OCT image of the anterior segment of the eye and the low signal-to-noise ratio area of the OCT image of the anterior segment of the eye, such as weak signals at two sides of the cornea and central supersaturation artifact caused by a telecentric scanning mode, so as to determine the edge profile of the tissue of the anterior segment of the eye, the processing speed is slower, the calculation precision of the inclination angle is not high due to the small number of extracted characteristic angular points, and the measurement precision and the rapidity of the cornea curvature and the central cornea thickness of the tissue of the anterior segment of the eye are reduced, so that the requirements of clinical precision and real-time of ophthalmic diseases can not be met at the same time.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an anterior ocular segment OCT image processing method that enables processing of non-whole images to determine anterior ocular segment tissue edge contours.
The application provides a method for processing OCT images of anterior ocular segments, which comprises the following steps: s1, manufacturing a self-adaptive template to acquire OCT images of anterior ocular segment in three characteristic areas; s2, obtaining edge contour data of the OCT image of the anterior ocular segment in three characteristic areas according to the acquired OCT image of the anterior ocular segment by an image preprocessing algorithm; s3, extracting edge contour data of OCT images of the anterior ocular segment in the three obtained characteristic areas to obtain first characteristic corner points of the OCT images of the anterior ocular segment; s4, extracting an OCT image of the anterior segment of the eye in the first characteristic angular point area based on the acquired first characteristic angular point, and extracting a second characteristic angular point through an edge detection algorithm; s5, selecting a third characteristic corner point of the OCT image of the anterior segment of the eye based on the first characteristic corner point and the second characteristic corner point, and calculating according to the third characteristic corner point to obtain the inclination angle and the inclination axis of the OCT image of the anterior segment of the eye.
Specifically, the step S1 includes:
step S11, selecting three characteristic areas based on eye structures of human eyes, wherein the three characteristic areas comprise: eye white to iris to pupil area, pupil center area, pupil to iris to eye white area;
and S12, manufacturing three characteristic area self-adaptive templates under the OCT image pixel coordinate system of the anterior segment.
Specifically, the step S2 includes:
step S21, performing image and operation on the OCT image of the anterior ocular segment and the three characteristic region self-adaptive templates to obtain anterior ocular segments in the three characteristic regionsOCT image-saving deviceRepresentation of->；
Step S22, performing an image preprocessing algorithm, including performing image enhancement, image convolution, binarization and contour extraction on the OCT images of the anterior ocular segment in the three feature areas to obtain edge contour images of the OCT images of the anterior ocular segment in the three feature areasThe OCT image edge profile of the anterior ocular segment in three feature regions.
Specifically, the step S3 includes:
step S31, making an eye white-to-iris-to-pupil characteristic region self-adaptive templateManufacturing self-adaptive template for pupil-to-iris-to-eye white characteristic region>；
Step S32, by image AND operation, namelyObtaining an OCT image edge contour image of the anterior ocular segment in the characteristic region from the white eye to the iris to the pupil +.>Through image and operation, namely->Obtaining an OCT image edge contour image of anterior ocular segment in the pupil-to-iris-to-eye white characteristic region +.>；
Step S33, obtaining the outline of the OCT image of the anterior ocular segment in the characteristic region from the eye white to the iris to the pupil through outline fillingFilling in an imageContour filling image of OCT image of anterior ocular segment in pupil-to-iris-to-eye white characteristic region is obtained by contour filling>；
Step S34, filling the outline of the OCT image in the characteristic region from white to iris to pupilIn (1), find the minimum and maximum of column y, i.e. +.>、/>By filling columnsObtaining maximum and minimum filling outline image of OCT image of anterior ocular segment in characteristic region from white to iris to pupil +.>The method comprises the steps of carrying out a first treatment on the surface of the OCT image edge contour image of anterior ocular segment in pupil-to-iris-to-eye white characteristic regionIn (1), find the minimum and maximum of column y, i.e. +.>、/>By filling columnsObtaining maximum and minimum filling outline image of OCT image of anterior ocular segment in pupil-to-iris-to-eye white characteristic region +.>；
Step S35, by image subtraction operation, namelyObtaining an internal contour image of the edge of the OCT image of the anterior ocular segment in the characteristic region from the white to the iris to the pupil +.>The method comprises the steps of carrying out a first treatment on the surface of the By image subtraction operation, i.e.Obtaining an internal contour image of the edge of the OCT image of the anterior ocular segment in the pupil-to-iris-to-eye white feature region +.>；
Step S36, performing OCT image processing on the inner contour image of the edge of the anterior ocular segment OCT image in the characteristic region from white to iris to pupilExtracting the maximum area contour to obtain a contour data point, and selecting the pixel coordinate with the minimum row xAs the first characteristic corner of cornea left, selecting the pixel coordinate with the maximum column y +.>As a first characteristic angular point of the left side of the crystal;
step S37, by imaging the inner contour of the edge of the OCT image of the anterior segment of the eye in the pupil-to-iris-to-eye white characteristic regionExtracting the maximum area contour to obtain a contour data point, and selecting the pixel coordinate with the maximum row xAs the first characteristic corner of cornea right, selecting the pixel coordinate with the maximum column y +.>As the right first characteristic corner of the crystal.
Specifically, the first feature corner includes: cornea left first characteristic angular point, crystal left first characteristic angular point, cornea right first characteristic angular point, crystal right first characteristic angular point.
Specifically, the step S4 includes:
step S41, taking the first characteristic angular point as a center, and extracting to obtain an OCT image of the anterior ocular segment of the first characteristic angular point region;
step S42, obtaining edge contour data of the OCT image of the anterior ocular segment of the first characteristic corner region through an image edge extraction algorithm: the image edge extraction algorithm comprises image enhancement, gaussian difference, morphological edge extraction and maximum area contour extraction;
and step S43, extracting characteristic corner points of the OCT image of the anterior segment of the eye, which are called second characteristic corner points.
Specifically, the first characteristic angular point region anterior ocular segment OCT image includes: taking the left first characteristic angular point of the cornea as a center to extract an OCT image of a front eye of a left first characteristic angular point region of the cornea, taking the right first characteristic angular point of the cornea as a center to extract an OCT image of a front eye of a right first characteristic angular point region of the cornea, taking the left first characteristic angular point of the crystal as a center to extract an OCT image of a front eye of a left first characteristic angular point region of the crystal, and taking the right first characteristic angular point of the crystal as a center to extract an OCT image of a front eye of a right first characteristic angular point region of the crystal.
Specifically, the edge profile data of the first characteristic corner area anterior ocular segment OCT image includes: the OCT image contour data of the anterior ocular segment of the left first characteristic angular point region of the cornea, the OCT image contour data of the anterior ocular segment of the right first characteristic angular point region of the cornea, the OCT image contour data of the anterior ocular segment of the left first characteristic angular point region of the crystal, and the OCT image contour data of the anterior ocular segment of the right first characteristic angular point region of the crystal.
Specifically, the step S43 includes:
selecting the most significant column y from the OCT image contour data of the anterior ocular segment in the left first characteristic corner region of the corneaPixel coordinatesAs a cornea left second characteristic angular point, selecting a pixel coordinate ++f with the largest column y from OCT image contour data of anterior ocular segment of a crystal left first characteristic angular point region>As a second characteristic angular point of the left side of the crystal, selecting a pixel coordinate with the largest column y from OCT image contour data of the anterior ocular segment of the right first characteristic angular point region of the corneaAs a second characteristic angular point of the right cornea, selecting a pixel coordinate ++f with the largest column y from OCT image contour data of the anterior ocular segment of the first characteristic angular point region of the right cornea of the crystal>As the second characteristic corner of the crystal.
Specifically, the step S5 includes:
step S51, selecting a characteristic corner point of the OCT image of the anterior segment of the eye from the first characteristic corner point and the second characteristic corner point through comparative analysis, namely a third characteristic corner point, and selecting pixel coordinates with smaller row x from the first characteristic corner point of the cornea left and the second characteristic corner point of the cornea left as the third characteristic corner point of the cornea left; selecting pixel coordinates with larger row x from the first characteristic corner point on the right of the cornea and the second characteristic corner point on the right of the cornea as a third characteristic corner point on the right of the cornea; selecting a pixel coordinate with smaller x as a left third characteristic angular point of the crystal from the left first characteristic angular point of the crystal and the left second characteristic angular point of the crystal; selecting a pixel coordinate with larger x from the first characteristic angular point on the right of the crystal and the second characteristic angular point on the right of the crystal as a third characteristic angular point on the right of the crystal; the third feature corner includes: cornea left third characteristic angular point, crystal left third characteristic angular point, cornea right third characteristic angular point, crystal right third characteristic angular point;
step S52, obtaining the tilt angle and tilt axis of the OCT image of the anterior segment of the eye by adopting a tilt angle calculation method: calculating a perpendicular bisector of a line segment formed by a left third characteristic corner point of the cornea and a right third characteristic corner point of the cornea as an inclined axis 1, and calculating an inclined angle of the line segment formed by the left third characteristic corner point of the cornea and the right third characteristic corner point of the cornea as an inclined angle 1; calculating a perpendicular bisector of a line segment formed by a left third characteristic angular point of the crystal and a right third characteristic angular point of the crystal as an inclined axis 2, and calculating an inclined angle of the line segment formed by the left third characteristic angular point of the crystal and the right third characteristic angular point of the crystal as an inclined angle 2;
step S53, the average value of the inclination angle 1 and the inclination angle 2 is the inclination angle of the OCT image of the anterior segment of the eye, and the intersection point of the inclination angle 1 and the inclination angle 2 is calculated, and the straight line passing through the intersection point and having the inclination angle is the inclination angle.
The application realizes the processing method of processing the non-whole image to determine the outline of the anterior segment tissue edge based on the self-adaptive template, can extract a large number of characteristic angular points so as to improve the calculation precision of the inclination angle, improves the measurement precision and rapidity of the anterior segment tissue to measure the cornea curvature and the central cornea thickness, and realizes the clinical precision and real-time of the ophthalmic diseases.
Drawings
FIG. 1 is a flow chart of a method of OCT image processing for anterior ocular segment according to the present application;
fig. 2 is a schematic diagram of three feature areas of a human eye structure selection set according to an embodiment of the present application;
fig. 3 is a schematic view of an OCT image of the anterior segment of the eye according to an embodiment of the present application;
FIG. 4 is a schematic diagram of three feature region adaptive templates provided in an embodiment of the present application;
FIG. 5 is a schematic flow chart of image preprocessing according to an embodiment of the present application;
FIG. 6 is a schematic diagram of an adaptive template for an eye white to iris to pupil feature region provided by an embodiment of the present application;
fig. 7 is a schematic diagram of a pupil-to-iris-to-eye white feature region adaptive template according to an embodiment of the present application;
FIG. 8 is a schematic diagram of edge profile data of OCT images of the anterior ocular segment in three feature regions according to an embodiment of the present application;
fig. 9 is a schematic diagram of a contour fill image of an OCT image of the anterior segment of the eye in the region from white to iris to pupil features provided in an embodiment of the present application;
fig. 10 is a schematic diagram of a maximum and minimum filling contour image of an OCT image of the anterior segment of the eye in a characteristic region from white to iris to pupil according to an embodiment of the present application;
FIG. 11 is a schematic view of an internal contour image of the edge of an OCT image of the anterior segment of the eye in the region from white to iris to pupil features provided by an embodiment of the present application;
fig. 12 is a schematic diagram of a contour fill image of an OCT image of the anterior segment of the eye in a pupil-to-iris-to-eye white feature region provided by an embodiment of the present application;
fig. 13 is a schematic diagram of a maximum and minimum filling contour image of an OCT image of the anterior segment of the eye in a pupil-to-iris-to-eye white feature region according to an embodiment of the present application;
fig. 14 is a schematic view of an internal contour image of an edge of an OCT image of the anterior segment of the eye in a pupil-to-iris-to-eye white feature region according to an embodiment of the present application;
fig. 15 is a schematic view of a first feature corner of an OCT image of the anterior segment of the eye according to an embodiment of the present application;
fig. 16 (a) and fig. 16 (b) are schematic diagrams of OCT image of anterior ocular segment in the first characteristic corner area of the cornea and OCT image profile data of anterior ocular segment in the first characteristic corner area of the cornea according to the embodiments of the present application, respectively;
fig. 17 (a) and fig. 17 (b) are schematic diagrams of OCT image of anterior ocular segment in the first right feature corner area of cornea and OCT image profile data of anterior ocular segment in the first right feature corner area of cornea according to the embodiments of the present application, respectively;
fig. 18 (a) and fig. 18 (b) are schematic diagrams of OCT image of anterior ocular segment in the first characteristic angular point region of the left crystal and OCT image profile data of anterior ocular segment in the first characteristic angular point region of the left crystal according to the embodiments of the present application, respectively;
fig. 19 (a) and fig. 19 (b) are schematic diagrams of OCT image of anterior ocular segment in the first right characteristic angular point region of the crystal and OCT image profile data of anterior ocular segment in the first right characteristic angular point region of the crystal according to the embodiment of the present application, respectively;
FIG. 20 is a schematic diagram of an edge detection algorithm according to an embodiment of the present application;
fig. 21 is a schematic view of a second feature corner of an OCT image of the anterior segment of the eye according to an embodiment of the present application;
fig. 22 is a schematic view of a third feature corner of an OCT image of the anterior segment of the eye according to an embodiment of the present application;
FIG. 23 is a schematic view showing the tilt angle and tilt axis calculated from the third corner point of the left cornea and the third corner point of the right cornea according to the embodiment of the present application;
FIG. 24 is a schematic view of tilt angles and tilt axes calculated by the third characteristic corner point on the left side of the crystal and the third characteristic corner point on the right side of the crystal according to an embodiment of the present application;
FIG. 25 is a schematic view of the resulting tilt angle and tilt axis provided by an embodiment of the present application.
Detailed Description
The application will be described in further detail with reference to the accompanying drawings and specific examples.
Referring to fig. 1, a flowchart of an embodiment of the method for processing OCT images of the anterior segment of the eye is shown.
Step S1, a self-adaptive template is manufactured to acquire OCT images of the anterior ocular segment in three characteristic areas. Namely, three feature region adaptive templates are made: three characteristic areas are selected based on the eyeball structure of the human eye, and three characteristic area self-adaptive templates are manufactured under the OCT image pixel coordinate system of the anterior segment of the eye.
The method specifically comprises the following steps:
step S11, three characteristic areas are selected based on the eyeball structure of the human eye, please refer to FIG. 2, wherein the area from the eye white to the iris to the pupil area, the pupil center area and the pupil to the iris to the eye white area are included, the area from the eye white to the iris to the pupil area includes the eye white, the iris and the pupil, the area is observed from left to right, firstly the eye white is seen, secondly the iris is seen, and finally the pupil is seen; pupil to iris to eye white region includes pupil, iris and eye white, viewing the region from left to right, first seeing pupil, second seeing iris, last seeing pupil; the pupil center area contains only the pupil; the anterior ocular segment OCT image of this embodiment is shown in fig. 3.
Step S12, three characteristic region adaptive templates are manufactured under the OCT image pixel coordinate system of the anterior segment of the eye as shown in FIG. 4, and the method adoptsAn x-th row and a y-th column pixel point representing an OCT image of the anterior segment of the eye, wherein the image size is +.>Respectively converting the length and the width of the three characteristic areas into an OCT image pixel coordinate system to manufacture three characteristic area self-adaptive templates, wherein the image pixel points of the three characteristic area self-adaptive templates are +.>Three feature regions are denoted by z, where: />，。
And S2, obtaining the edge contour data of the OCT image of the anterior ocular segment in the three characteristic areas according to the acquired OCT image of the anterior ocular segment by an image preprocessing algorithm. That is, the anterior ocular segment OCT image edge profile data in three feature regions is acquired: based on the three characteristic area self-adaptive templates, extracting the OCT images of the anterior ocular segment in the three characteristic areas from the OCT images of the anterior ocular segment obtained by the OCT equipment, and obtaining the edge contour data of the OCT images of the anterior ocular segment in the three characteristic areas by an image preprocessing method.
The method specifically comprises the following steps:
step S21, performing image and operation on the OCT image of the anterior segment and three characteristic region adaptive templates to obtain OCT images of the anterior segment in the three characteristic regionsRepresentation of->；
Step S22, performing an image preprocessing algorithm, please refer toFig. 5 shows that the image enhancement (S201), the image convolution (S202), the binarization (S203) and the contour extraction (S204) are performed on the OCT images of the anterior segment of the eye in the three feature regions, and the edge contour image of the OCT images of the anterior segment of the eye in the three feature regions is obtainedThe OCT image edge contour of the anterior ocular segment in the three characteristic regions;
wherein, the convolution kernel of the image convolution is kernel= [ 010; 1, 5, 1; 0, 1).
And S3, extracting edge contour data of the OCT image of the anterior ocular segment in the three obtained characteristic areas to obtain a first characteristic corner point of the OCT image of the anterior ocular segment. The method specifically comprises the following steps:
step S31, making an adaptive template (shown in FIG. 6) for the characteristic region from white to iris to pupilRepresenting the creation of a pupil to iris to eye white feature region adaptive template (as shown in FIG. 7)>A representation;
step S32, by image AND operation, namelyObtaining the edge contour image of the OCT image of the anterior ocular segment in the characteristic region from the white eye to the iris to the pupil, namely +.>Through image and operation, namely->Obtaining the edge contour image of the OCT image of the anterior ocular segment in the characteristic region from pupil to iris to eye white, namely +.>(as shown in fig. 8);
step S33, obtaining the anterior segment O of the eye in the characteristic region from the white to the iris to the pupil through contour fillingThe contour fill image of the CT image (as shown in FIG. 9), i.e.Contour filling image (shown in fig. 12) of eye anterior segment OCT image from pupil to iris to eye white characteristic region is obtained by contour filling>；
Step S34, the OCT image edge contour image of the anterior segment of the eye (as shown in FIG. 10) in the characteristic region from white to iris to pupilIn (1), find the minimum and maximum of column y, i.e. +.>、/>By filling columnsObtaining the maximum and minimum filling outline image of the OCT image of the anterior ocular segment in the characteristic region from the white eye to the iris to the pupil, namely +.>The method comprises the steps of carrying out a first treatment on the surface of the OCT image edge contour image of anterior ocular segment in pupil-to-iris-to-eye white characteristic region, namelyIn (1), find the minimum and maximum of column y, i.e. +.>、/>By filling columnsObtaining the maximum and minimum filling outline of OCT image of anterior ocular segment in the characteristic region from pupil to iris to eye whiteAn image (as shown in FIG. 13) is +.>；
Step S35, by image subtraction operation, namelyObtaining an internal contour image (shown in figure 11) of the edge of the OCT image of the anterior ocular segment in the characteristic region from the white to the iris to the pupil, namely +.>The method comprises the steps of carrying out a first treatment on the surface of the By image subtraction operation, i.e.)>Obtaining an internal contour image (shown in figure 14) of the edge of the OCT image of the anterior ocular segment in the pupil-to-iris-to-eye white characteristic region, namely +.>；
Step S36, the internal contour image of the OCT image edge of the anterior segment of the eye in the characteristic region from white to iris to pupil, namelyExtracting the maximum area contour to obtain contour data points, and selecting the pixel coordinate with the smallest row x, namely +.>As the first characteristic corner point of cornea left, selecting the pixel coordinate with the largest column y, namelyAs a first characteristic angular point of the left side of the crystal;
step S37, by applying the OCT image to the inner contour image of the edge of the anterior ocular segment in the pupil-to-iris-to-eye white characteristic region, namelyExtracting the maximum area contour to obtain contour data points, and selecting the pixel coordinate with the maximum row x, namely +.>As the first characteristic corner point of cornea right, selecting the pixel coordinate with the largest column y, namelyAs the right first characteristic angular point of the crystal;
the first characteristic corner points on the left of the cornea, the first characteristic corner points on the left of the crystal, the first characteristic corner points on the right of the cornea and the first characteristic corner points on the right of the crystal are first characteristic corner points (shown in fig. 15).
And S4, extracting an OCT image of the anterior segment of the eye in the first characteristic corner area based on the acquired first characteristic corner, and extracting a second characteristic corner through an edge detection algorithm. That is, the first characteristic corner area anterior ocular segment OCT image of the anterior ocular segment OCT image obtained by the OCT apparatus is extracted centering on the first characteristic corner of the anterior ocular segment OCT image obtained by the step S3, the edge contour data point of the first characteristic corner area anterior ocular segment OCT image of the anterior ocular segment OCT image obtained by the OCT apparatus is obtained by the image edge extraction algorithm, and the second characteristic corner of the anterior ocular segment OCT image obtained by the OCT apparatus is extracted.
The method specifically comprises the following steps:
step S41, taking the first feature corner as the center, and extracting to obtain an OCT image of the anterior ocular segment of the first feature corner region as shown in fig. 16 (a): the method includes extracting an OCT image of a front eye segment of a left first feature corner region of the cornea with the left first feature corner of the cornea as a center as shown in fig. 18 (a), extracting an OCT image of a front eye segment of a right first feature corner region of the cornea with the right first feature corner of the cornea as a center as shown in fig. 17 (a), extracting an OCT image of a front eye segment of a left first feature corner region of the crystal with the left first feature corner of the crystal as a center, and extracting an OCT image of a front eye segment of a right first feature corner region of the crystal with the right first feature corner of the crystal as a center as shown in fig. 19 (a);
step S42, as shown in fig. 20, obtaining edge contour data points of the OCT image of the anterior segment of the eye in the first feature corner region through an image edge extraction algorithm: the method comprises the steps of obtaining OCT image contour data of a left first characteristic angular point region of a cornea as shown in fig. 16 (b), OCT image contour data of a right first characteristic angular point region of the cornea as shown in fig. 17 (b), OCT image contour data of a left first characteristic angular point region of a crystal as shown in fig. 18 (b), OCT image contour data of a right first characteristic angular point region of the cornea as shown in fig. 19 (b), wherein an image edge extraction algorithm comprises image enhancement, gaussian difference, morphological edge extraction and maximum area contour extraction;
step S43, extracting a feature corner of the anterior segment OCT image, called a second feature corner, includes: selecting the pixel coordinate with the largest column y from the OCT image contour data of the anterior ocular segment in the left first characteristic angular point region of the cornea, namelyAs shown in fig. 21, the second characteristic corner point of the cornea is shown as a left characteristic corner point region of the cornea, and the pixel coordinate with the largest column y is selected from OCT image contour data of the anterior ocular segment of the first characteristic corner point region of the cornea, namely +.>As a second characteristic angular point of the left side of the crystal, as shown in fig. 21, a pixel coordinate with the largest column y is selected from OCT image contour data of anterior ocular segment of the right first characteristic angular point region of cornea, namely +.>As a second characteristic angular point of the right cornea, as shown in fig. 21, selecting the pixel coordinate with the largest column y, namely +_in the OCT image contour data of the anterior ocular segment of the region of the first characteristic angular point of the right cornea of the crystal>As a second characteristic angular point of the crystal, the right characteristic angular point is shown in fig. 21;
the second feature corner includes: cornea left second characteristic angular point, crystal left second characteristic angular point, cornea right second characteristic angular point, crystal right second characteristic angular point.
And S5, selecting a third characteristic corner point of the OCT image of the anterior segment of the eye based on the first characteristic corner point and the second characteristic corner point, and calculating according to the third characteristic corner point to obtain the inclination angle and the inclination axis of the OCT image of the anterior segment of the eye. That is, the third feature corner is acquired and the tilt angle is calculated: and in the first characteristic corner point and the second characteristic corner point, selecting a third characteristic corner point of the OCT image of the anterior segment of the eye through comparative analysis, calculating the inclination angle of a perpendicular bisector of a connecting line of the corresponding two points in the third characteristic corner point, obtaining the inclination angle of the OCT image of the anterior segment of the eye through calculating the average value of the inclination angles, and obtaining the inclination axis of the OCT image of the anterior segment of the eye through calculating the intersection point of the perpendicular bisector.
The method specifically comprises the following steps:
step S51, selecting a characteristic corner point of the OCT image of the anterior segment of the eye from the first characteristic corner point and the second characteristic corner point through comparative analysis, wherein the characteristic corner point is called a third characteristic corner point as shown in fig. 22, and selecting pixel coordinates with smaller row x as the left third characteristic corner point of the cornea from the left first characteristic corner point of the cornea and the left second characteristic corner point of the cornea; selecting pixel coordinates with larger row x from the first characteristic corner point on the right of the cornea and the second characteristic corner point on the right of the cornea as a third characteristic corner point on the right of the cornea; selecting a pixel coordinate with smaller x as a left third characteristic angular point of the crystal from the left first characteristic angular point of the crystal and the left second characteristic angular point of the crystal; selecting a pixel coordinate with larger x from the first characteristic angular point on the right of the crystal and the second characteristic angular point on the right of the crystal as a third characteristic angular point on the right of the crystal; the third feature corner includes: cornea left third characteristic angular point, crystal left third characteristic angular point, cornea right third characteristic angular point, crystal right third characteristic angular point;
it should be noted that, the third characteristic angular point of the anterior segment OCT image is obtained by comparing and selecting from the first characteristic angular point and the second characteristic angular point; therefore, compared with the first characteristic corner point and the second characteristic corner point, the third characteristic corner point can more accurately represent the characteristic corner point of the OCT image of the anterior segment of the eye, namely, the accuracy of the third characteristic corner point is higher;
step S52, obtaining the inclination angle and the inclination axis of the OCT image of the anterior ocular segment by adopting an inclination angle calculation method, wherein the inclination angle and the inclination axis comprise calculating the inclination angle of a line segment formed by a left third characteristic angular point of the cornea and a right third characteristic angular point of the cornea as the inclination axis 1, and the inclination angle of a line segment formed by the left third characteristic angular point of the cornea and the right third characteristic angular point of the cornea is calculated as the inclination angle 1 as shown in FIG. 23; calculating a perpendicular bisector of a line segment formed by a left third characteristic angular point of the crystal and a right third characteristic angular point of the crystal as an inclined axis 2, and calculating an inclined angle of the line segment formed by the left third characteristic angular point of the crystal and the right third characteristic angular point of the crystal as an inclined angle 2, wherein the inclined angle is shown in fig. 24;
step S53, the tilt angle 1 and the tilt angle 2 are averaged to obtain the tilt angle of the OCT image of the anterior segment of the eye, and the intersection point of the tilt axis 1 and the tilt axis 2 is calculated, and the straight line passing through the intersection point and having the tilt of the tilt angle is the tilt axis, as shown in FIG. 25.
While the application 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 application are intended to be included within the scope of the appended claims.

Claims (7)

1. An anterior ocular segment OCT image processing method, comprising the steps of:
s1, manufacturing a self-adaptive template to acquire OCT images of anterior ocular segment in three characteristic areas;
s2, obtaining edge contour data of the OCT image of the anterior ocular segment in three characteristic areas according to the acquired OCT image of the anterior ocular segment by an image preprocessing algorithm;
s3, extracting edge contour data of OCT images of the anterior ocular segment in the three obtained characteristic areas to obtain first characteristic corner points of the OCT images of the anterior ocular segment;
s4, extracting an OCT image of the anterior segment of the eye in the first characteristic angular point area based on the acquired first characteristic angular point, and extracting a second characteristic angular point through an edge detection algorithm;
s5, selecting a third characteristic corner point of the OCT image of the anterior segment of the eye based on the first characteristic corner point and the second characteristic corner point, and calculating according to the third characteristic corner point to obtain an inclined angle and an inclined axis of the OCT image of the anterior segment of the eye;
the step S1 comprises the following steps:
step S11, selecting three characteristic areas based on eye structures of human eyes, wherein the three characteristic areas comprise: eye white to iris to pupil area, pupil center area, pupil to iris to eye white area;
step S12, three characteristic area self-adaptive templates are manufactured under an OCT image pixel coordinate system of the anterior segment of the eye;
the step S2 includes:
step S21, performing image and operation on the OCT image of the anterior segment and three characteristic region adaptive templates to obtain OCT images of the anterior segment in the three characteristic regions, usingRepresentation of->The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing the x-th row and y-th column pixel points of the OCT image of the anterior ocular segment; />Representing image pixels of the adaptive template;
step S22, performing an image preprocessing algorithm, including performing image enhancement, image convolution, binarization and contour extraction on the OCT images of the anterior ocular segment in the three feature areas to obtain edge contour images of the OCT images of the anterior ocular segment in the three feature areasThe OCT image edge contour of the anterior ocular segment in the three characteristic regions;
the step S3 includes:
step S31, making an eye white-to-iris-to-pupil characteristic region self-adaptive templateManufacturing self-adaptive template for pupil-to-iris-to-eye white characteristic region>；
Step S32, through image AND operationObtaining an OCT image edge contour image of the anterior ocular segment in the characteristic region from the white eye to the iris to the pupil +.>Through image and operation->Obtaining an OCT image edge contour image of anterior ocular segment in the pupil-to-iris-to-eye white characteristic region +.>；
Step S33, obtaining a contour filling image of the anterior ocular segment OCT image in the characteristic region from the eye white to the iris to the pupil through contour fillingContour filling image of OCT image of anterior ocular segment in pupil-to-iris-to-eye white characteristic region is obtained by contour filling>；
Step S34, filling the outline of the OCT image in the characteristic region from white to iris to pupilIn (1), find the minimum and maximum of column y, i.e. +.>、/>By filling columns->Obtaining maximum and minimum filling outline image of OCT image of anterior ocular segment in characteristic region from white to iris to pupil +.>The method comprises the steps of carrying out a first treatment on the surface of the OCT image edge contour image of anterior ocular segment in pupil-to-iris-to-eye white feature region +.>In (1), find the minimum and maximum of column y, i.e. +.>、/>By filling columns->Obtaining maximum and minimum filling outline image of OCT image of anterior ocular segment in pupil-to-iris-to-eye white characteristic region +.>；
Step S35, through image subtraction operationObtaining an internal contour image of the edge of the OCT image of the anterior ocular segment in the characteristic region from the white to the iris to the pupil +.>The method comprises the steps of carrying out a first treatment on the surface of the By image subtraction operationsObtaining an internal contour image of the edge of the OCT image of the anterior ocular segment in the pupil-to-iris-to-eye white feature region +.>；
Step S36, performing OCT image processing on the inner contour image of the edge of the anterior ocular segment OCT image in the characteristic region from white to iris to pupilExtracting the maximum area contour to obtain a contour data point, and selecting the pixel coordinate with the minimum row xAs the first characteristic corner of cornea left, selecting the pixel coordinate with the maximum column y +.>As a first characteristic angular point of the left side of the crystal;
step S37, by imaging the inner contour of the edge of the OCT image of the anterior segment of the eye in the pupil-to-iris-to-eye white characteristic regionExtracting the maximum area contour to obtain a contour data point, and selecting the pixel coordinate with the maximum row xAs the first characteristic corner of cornea right, selecting the pixel coordinate with the maximum column y +.>As the right first characteristic corner of the crystal.
2. The method of claim 1, wherein the first feature corner comprises: cornea left first characteristic angular point, crystal left first characteristic angular point, cornea right first characteristic angular point, crystal right first characteristic angular point.
3. The method of claim 2, wherein said step S4 comprises:
step S41, taking the first characteristic angular point as a center, and extracting to obtain an OCT image of the anterior ocular segment of the first characteristic angular point region;
step S42, obtaining edge contour data of the OCT image of the anterior ocular segment of the first characteristic corner region through an image edge extraction algorithm: the image edge extraction algorithm comprises image enhancement, gaussian difference, morphological edge extraction and maximum area contour extraction;
and step S43, extracting characteristic corner points of the OCT image of the anterior segment of the eye, which are called second characteristic corner points.
4. A method as claimed in claim 3, wherein the first feature corner region anterior ocular segment OCT image comprises: taking the left first characteristic angular point of the cornea as a center to extract an OCT image of a front eye of a left first characteristic angular point region of the cornea, taking the right first characteristic angular point of the cornea as a center to extract an OCT image of a front eye of a right first characteristic angular point region of the cornea, taking the left first characteristic angular point of the crystal as a center to extract an OCT image of a front eye of a left first characteristic angular point region of the crystal, and taking the right first characteristic angular point of the crystal as a center to extract an OCT image of a front eye of a right first characteristic angular point region of the crystal.
5. The method of claim 4, wherein the edge profile data of the first feature corner region anterior ocular segment OCT image comprises: the OCT image contour data of the anterior ocular segment of the left first characteristic angular point region of the cornea, the OCT image contour data of the anterior ocular segment of the right first characteristic angular point region of the cornea, the OCT image contour data of the anterior ocular segment of the left first characteristic angular point region of the crystal, and the OCT image contour data of the anterior ocular segment of the right first characteristic angular point region of the crystal.
6. The method of claim 5, wherein said step S43 comprises:
selecting the pixel coordinate with the largest column y from OCT image contour data of anterior ocular segment in the left first characteristic angular point region of corneaAs the left second characteristic angular point of cornea, selecting OCT image contour data of anterior ocular segment in the left first characteristic angular point region of crystalColumn y maximum pixel coordinate +.>As a second characteristic angular point of the left side of the crystal, selecting a pixel coordinate with the largest column y from OCT image contour data of the anterior ocular segment of the right first characteristic angular point region of the corneaAs a second characteristic angular point of the right cornea, selecting a pixel coordinate ++f with the largest column y from OCT image contour data of the anterior ocular segment of the first characteristic angular point region of the right cornea of the crystal>As the second characteristic corner of the crystal.
7. The method of claim 6, wherein said step S5 comprises:
step S51, selecting a characteristic corner point of the OCT image of the anterior segment of the eye from the first characteristic corner point and the second characteristic corner point through comparative analysis, namely a third characteristic corner point, and selecting pixel coordinates with smaller row x from the first characteristic corner point of the cornea left and the second characteristic corner point of the cornea left as the third characteristic corner point of the cornea left; selecting pixel coordinates with larger row x from the first characteristic corner point on the right of the cornea and the second characteristic corner point on the right of the cornea as a third characteristic corner point on the right of the cornea; selecting a pixel coordinate with smaller x as a left third characteristic angular point of the crystal from the left first characteristic angular point of the crystal and the left second characteristic angular point of the crystal; selecting a pixel coordinate with larger x from the first characteristic angular point on the right of the crystal and the second characteristic angular point on the right of the crystal as a third characteristic angular point on the right of the crystal; the third feature corner includes: cornea left third characteristic angular point, crystal left third characteristic angular point, cornea right third characteristic angular point, crystal right third characteristic angular point;
step S52, obtaining the tilt angle and tilt axis of the OCT image of the anterior segment of the eye by adopting a tilt angle calculation method: calculating a perpendicular bisector of a line segment formed by a left third characteristic corner point of the cornea and a right third characteristic corner point of the cornea as an inclined axis 1, and calculating an inclined angle of the line segment formed by the left third characteristic corner point of the cornea and the right third characteristic corner point of the cornea as an inclined angle 1; calculating a perpendicular bisector of a line segment formed by a left third characteristic angular point of the crystal and a right third characteristic angular point of the crystal as an inclined axis 2, and calculating an inclined angle of the line segment formed by the left third characteristic angular point of the crystal and the right third characteristic angular point of the crystal as an inclined angle 2;
step S53, the average value of the inclination angle 1 and the inclination angle 2 is the inclination angle of the OCT image of the anterior segment of the eye, and the intersection point of the inclination angle 1 and the inclination angle 2 is calculated, and the straight line passing through the intersection point and having the inclination angle is the inclination angle.
CN202310580898.3A 2023-05-23 2023-05-23 OCT image processing method for anterior ocular segment Active CN116309594B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310580898.3A CN116309594B (en) 2023-05-23 2023-05-23 OCT image processing method for anterior ocular segment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310580898.3A CN116309594B (en) 2023-05-23 2023-05-23 OCT image processing method for anterior ocular segment

Publications (2)

Publication Number Publication Date
CN116309594A CN116309594A (en) 2023-06-23
CN116309594B true CN116309594B (en) 2023-08-15

Family

ID=86785423

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310580898.3A Active CN116309594B (en) 2023-05-23 2023-05-23 OCT image processing method for anterior ocular segment

Country Status (1)

Country Link
CN (1) CN116309594B (en)

Citations (5)

* Cited by examiner, † Cited by third party
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
JP2015089477A (en) * 2013-11-07 2015-05-11 大日本印刷株式会社 Image analysis device and method for determining ophthalmologic disease
JP2018120299A (en) * 2017-01-23 2018-08-02 富士通株式会社 Line-of-sight detection computer program, line-of-sight detection device and line-of-sight detection 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
CN110276750A (en) * 2019-06-17 2019-09-24 浙江大学 A kind of extraction of any inclination angle wafer straight line side length and crystal grain area partition method

Patent Citations (5)

* Cited by examiner, † Cited by third party
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
JP2015089477A (en) * 2013-11-07 2015-05-11 大日本印刷株式会社 Image analysis device and method for determining ophthalmologic disease
JP2018120299A (en) * 2017-01-23 2018-08-02 富士通株式会社 Line-of-sight detection computer program, line-of-sight detection device and line-of-sight detection 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
CN110276750A (en) * 2019-06-17 2019-09-24 浙江大学 A kind of extraction of any inclination angle wafer straight line side length and crystal grain area partition method

Also Published As

Publication number Publication date
CN116309594A (en) 2023-06-23

Similar Documents

Publication Publication Date Title
CN109345469B (en) Speckle denoising method in OCT imaging based on condition generation countermeasure network
Aquino et al. Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques
US9418423B2 (en) Motion correction and normalization of features in optical coherence tomography
CN111292338B (en) Method and system for segmenting choroidal neovascularization from fundus OCT image
US9655512B2 (en) Methods and systems to measure corneal epithelial thickness and power, stromal thickness, subepithelial corneal power and topography for disease diagnosis
CN108509908B (en) Pupil diameter real-time measurement method based on binocular stereo vision
TWI719587B (en) Pre-processing method and storage device for quantitative analysis of fundus image
CN108257126B (en) Blood vessel detection and registration method, equipment and application of three-dimensional retina OCT image
CN113643354B (en) Measuring device of vascular caliber based on fundus image with enhanced resolution
Cheng et al. Robust three-dimensional registration on optical coherence tomography angiography for speckle reduction and visualization
Mathai et al. Learning to segment corneal tissue interfaces in oct images
Niri et al. Multi-view data augmentation to improve wound segmentation on 3D surface model by deep learning
CN111583248B (en) Processing method based on eye ultrasonic image
CN116342636B (en) Eye anterior segment OCT image contour fitting method
CN116309594B (en) OCT image processing method for anterior ocular segment
Liu et al. Retinal vessel segmentation using densely connected convolution neural network with colorful fundus images
CN109492653B (en) Method and device for measuring breast lesion volume, computer equipment and storage medium
CN111861977A (en) Feature extraction method of anterior segment tomogram based on machine vision
JP2022513424A (en) Method of automatic shape quantification of optic disc
CN108269258B (en) Method and system for segmenting corneal structures from OCT corneal images
CN116309661B (en) Method for extracting OCT (optical coherence tomography) image contour of anterior segment of eye
WO2023103609A1 (en) Eye tracking method and apparatus for anterior segment octa, device, and storage medium
CN114373216B (en) Eye tracking method, device, equipment and storage medium for anterior segment OCTA
CN108231165A (en) A kind of auxiliary system of eye disease diagnosis
CN118015066A (en) OCT image-based boundary pixel height acquisition method and application of optical biological measuring instrument calibration device

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