IMPROVEMENTS TO FITTING ORTHOKERATOLOGY LENSES

• US 20200133023A1
• Filed: 06/28/2018
• Published: 04/30/2020
• Est. Priority Date: 06/28/2017
• Status: Active Grant

• Current Assignee: Capricornia Contact Lens Pty., Ltd.
• Original Assignee: Capricornia Contact Lens Pty., Ltd.
• Inventors: GIFFORD, Paul
• Granted Patent: US 11,573,432 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 3/0025 characterised by electronic signal processing, e.g. eye models
• CPC Class Codes: A61B 3/107 for determining the shape or measuring the curvature of the cornea
• CPC Class Codes: G02C 7/047 Contact lens fitting; Contact lenses for orthokeratology; Contact lenses for specially shaped corneae
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 2207/30041 Eye; Retina; Ophthalmic
• CPC Class Codes: G06T 7/0014 using an image reference approach

Abstract

A method for fitting OK lenses to a patient comprising the steps of: applying a corneal topography apparatus to a patient to capture baseline and post wear maps of a cornea of the patient in a computer to thereby derive a difference map; processing the difference map to fit Zernike polynomials thereto wherein weights of said fitted polynomials comprise features of a test feature vector for the difference map; applying the test feature vector to a classification machine trained to classify the difference map as one of a number of predetermined classes; and subsequently treating the patient taking into account the classification machine'"'"'s classification.

Claims

1-19. -19. (canceled)

20. A method to therapeutically treat an eye condition related to the shape of the cornea, the method comprising the steps of:

applying a corneal topography apparatus to a patient to capture a map of a cornea of the patient in a computer;

extracting one or more feature vectors from the map including at least features identifying a red ring of the cornea;

applying the one or more feature vectors to a classification machine trained to classify the difference map as one of at least;

i. “

bullseye”

OR “

central island”

, and

ii. “

smiley face”

, and

iii. “

frowney face”

, and

iv. “

lateral decentration”

; and

subsequently treating the patient taking into account the classification machine'"'"'s classification.

21. The method of claim 20, wherein the step of extracting the features identifying the red ring of the cornea include determining center coordinates of a circle fitted to a red ring observed in the map.

22. The method according of claim 20, wherein the step of extracting the features identifying the red ring of the cornea includes determining long and short axes of an ellipse fitted to the red ring.

23. The method of the claim 20, wherein the corneal topography map comprises a difference map, wherein the method includes the steps of:

applying the corneal topography apparatus to the patient to capture a baseline map of a cornea of the patient in the computer;

subsequent to the patient wearing an OK lens on the cornea applying the corneal topography apparatus to the patient to capture a post-wear map of the cornea in the computer; and

deriving the difference map from the baseline map and the post-wear map.

24. The method of claim 23, wherein the step of subsequently treating the patient taking into account a classification produced by the classification machine, includes fitting an OK lens to the patient wherein said lens is selected based on the classification machine'"'"'s classification of the difference map.

25. The method of claim 20, wherein the step of extracting one or more feature vectors from the difference map includes extracting curvature estimates of the difference map and applying the one or more features to a classification machine trained to classify the difference map as one of at least:

i. “

bullseye”

, and

ii. “

smiley face”

, and

iii. “

frowney face”

, and

iv. “

lateral decentration”

, and

v. “

central island”

.

26. The method of claim 25, including extracting curvature estimates of the difference map by fitting Zernike polynomials thereto.

27. The method of claim 26, including fitting Z4, Z7, Z8, Z12, Z17, Z18 and Z24 Zernike polynomials.

28. The method of claim 26, including obtaining features corresponding to 14 Zernike components from axial curvature difference map data measured over a 3.5 mm pupil,

29. The method of claim 28, including obtaining features corresponding to 14 Zernike components from axial curvature and tangential curvature difference maps data measured over a 5.5 mm pupil.

30. The method of claim 20, wherein the classification machine includes one of:

a Decision Forest;

Decision Jungle;

Logistic Regression Machine;

Neural Network;

Support Vector Machine.

31. An apparatus for classifying corneal topography maps into one of a number of classes including:

an input unit arranged to convert data generated by a corneal topographer into a corneal map;

a feature extraction unit responsive to the input unit and arranged to process the corneal map to produce a corresponding test feature vector, wherein the feature extraction unit is arranged to identify a red ring of the map and to fit one or more shapes to the red ring wherein parameters of said shapes comprise features of the feature vector;

a classification unit trained to classify test vectors for corneal maps and responsive to the feature extraction unit, wherein the classification unit is arranged to classify the test feature vector as one of at least;

I. “

bullseye”

OR “

central island”

, and

II. “

smiley face”

, and

III. “

frowney face”

, and

IV. “

lateral decentration”

; and

an electronic display that is responsive to the classification unit for presenting classifications to a human user.

32. The apparatus of claim 31, wherein the feature extraction unit is arranged to fit shapes comprising a circle and an ellipse to the red ring.

33. The apparatus of claim 32, wherein the feature extraction unit is arranged to process the corneal map to fit Zernike polynomials thereto

wherein weights of said fitted polynomials comprise further features of the test feature vector and

wherein the classification unit is trained to classify test vectors including said weights to classify the test feature vector as one of at least:

i. “

bullseye”

, and

ii. “

smiley face”

, and

iii. “

frowney face”

, and

iv. “

lateral decentration”

, and

v. “

central island”

.

35. The apparatus of claim 31 implemented by means of a cloud server platform.

34. A method for fitting OK lenses to a patient comprising the steps of:

applying a corneal topography apparatus to a patient to capture baseline and post wear maps of a cornea of the patient in a computer to thereby derive a difference map;

processing the difference map to fit Zernike polynomials thereto wherein weights of said fitted polynomials comprise features of a test feature vector for the difference map;

applying the test feature vector to a classification machine trained to classify the difference map as one of a number of classes; and

subsequently treating the patient taking into account the classification machine'"'"'s classification.

36. An apparatus for classifying corneal topography maps into one of a number of predetermined classes including:

an input unit for converting data from a corneal topography unit into a corneal map;

a feature extraction unit arranged to process the corneal map to fit Zernike polynomials thereto wherein weights of said fitted polynomials comprise further features of the test feature vector;

a classification unit trained to classify test vectors for corneal maps and responsive to the feature extraction unit,

wherein the classification unit is arranged to classify the test feature vector as corresponding to one of the number of predetermined classes”

; and

an electronic display that is responsive to the classification unit for presenting classifications to a human user.

37. The apparatus of claim 36 in combination with the corneal topography unit.

38. A method to therapeutically treat an eye condition related to the shape of the cornea, the method comprising the steps of:

applying a corneal topography apparatus to a patient to capture a map of a cornea of the patient in a computer;

processing the corneal map to fit Zernike polynomials thereto wherein weights of said fitted polynomials comprise features of the test feature vector;

applying the test feature vector to a classification machine trained to classify the difference map as one of a number of predetermined classes; and

subsequently treating the patient taking into account the classification machine'"'"'s classification.