Granted Patent B2

US 12,262,946 · App. 17/299,714 · Granted Apr 1, 2025

Inventor: John Gregory Ladas (Germantown, MD)

Assignee: Advanced Euclidean Solutions, LLC

A61B3/103A61B3/0025A61F2/16G16H50/20A61B3/125

Abstract

Claims (72)

1. An apparatus for intraocular lens selection, comprising:

a biometer configured to obtain at least two ocular measurement parameters for an eye;

a user interface configured to obtain a lens selection parameter for the eye;

an autorefractor configured to obtain a post-operative refraction of the eye;

a memory; and

a processor communicatively coupled to the biometer, the user interface, the autorefractor, and the memory, and configured to:

determine an intraocular lens power based on a formula using the at least two ocular measurement parameters; and

correlate the at least two ocular measurement parameters, the intraocular lens power, and the post-operative refraction as a training set; and

train a deep learning machine using the at least two ocular measurement parameters, the post-operative refraction of the eye, and the intraocular lens power of a plurality of training sets to determine an estimated error of the formula applied to at least two ocular measurement parameters of an eye of a new patient.

2. The apparatus of claim 1 , wherein the processor is configured to

determine an estimated error of the formula using a deep learning machine trained on verified post-operative results including post-operative refractions corresponding to intraocular lens powers;

adjust the lens selection parameter based on the estimated error; and

redetermine a final intraocular lens power based on the formula and the adjusted lens selection parameter.

3. The apparatus of claim 2 , wherein the processor is configured to include the final intraocular lens power in the training set.

4. The apparatus of claim 1 , wherein the lens selection parameter is one of a target refraction or A-constant.

5. The apparatus of claim 1 , wherein the at least two ocular measurement parameters are selected from the group consisting of: axial length, corneal power, corneal power index, and anterior chamber depth.

6. The apparatus of claim 1 , wherein the lens selection formula includes one or more of: a Hoffer Q formula, a Holladay I formula, a Haigis formula, and a SRK/T formula, a Barrett Universal II formula, or adjustments thereto.

7. The apparatus of claim 1 , wherein the ocular measurement parameters include intraoperative aberrometry measurements.

8. The apparatus of claim 1 , further comprising:

a display device, wherein the processor is configured to render the intraocular lens power on a relevant portion of a super surface including ideal or near ideal portions of a plurality of intraocular lens selection formulas based on a range of the at least two ocular measurement parameters most suitable to each individual intraocular lens selection formula.

9. A method of intraocular lens selection, comprising:

obtaining at least two ocular measurement parameters for an eye by a biometer;

obtaining a lens selection parameter for the eye;

determining an intraocular lens power based on a formula using the at least two ocular measurement parameters;

obtaining a post-operative refraction of the eye from an autorefractor communicatively coupled with the biometer; and

correlating the at least two ocular measurement parameters, the intraocular lens power, and the post-operative refraction as a training set; and

training a deep learning machine using the at least two ocular measurement parameters, the post-operative refraction of the eye, and the intraocular lens power of a plurality of training sets to determine an estimated error of the formula applied to at least two ocular measurement parameters of an eye of a new patient.

10. The method of claim 9 , further comprising:

determining an estimated error of the formula using a deep learning machine trained on verified post-operative results including post-operative refractions corresponding to intraocular lens powers;

adjusting the lens selection parameter based on the estimated error; and

redetermining a final intraocular lens power based on the formula and the adjusted lens selection parameter.

11. The method of claim 10 , wherein correlating the at least two ocular measurement parameters, the intraocular lens power, and the post-operative refraction as a training set comprises including the final intraocular lens power in the training set.

12. The method of claim 9 , wherein the lens selection parameter is one of a target refraction or A-constant.

13. The method of claim 9 , wherein the at least two ocular measurement parameters are selected from the group consisting of: axial length, corneal power, corneal power index, and anterior chamber depth.

14. The method of claim 9 , wherein the lens selection formula includes one or more of: a Hoffer Q formula, a Holladay I formula, a Haigis formula, and a SRK/T formula, a Barrett Universal II formula, or adjustments thereto.

15. The method of claim 9 , wherein the ocular measurement parameters include intraoperative aberrometry measurements.

16. A non-transitory computer-readable medium storing computer executable instructions, comprising instructions to cause a computer to:

obtain at least two ocular measurement parameters for an eye by a biometer;

obtain a lens selection parameter for the eye;

determine an intraocular lens power based on a formula using the at least two ocular measurement parameters;

obtain a post-operative refraction of the eye from an autorefractor communicatively coupled with the biometer;

correlate the at least two ocular measurement parameters, the intraocular lens power, and the post-operative refraction as a training set; and

train a deep learning machine using the at least two ocular measurement parameters, the post-operative refraction of the eye, and the intraocular lens power of a plurality of training sets to determine an estimated error of the formula applied to at least two ocular measurement parameters of an eye of a new patient.

17. The non-transitory computer-readable medium of claim 16 , further comprising instructions to cause the computer to:

determine an estimated error of the formula using a deep learning machine trained on verified post-operative results including post-operative refractions corresponding to intraocular lens powers;

adjust the lens selection parameter based on the estimated error; and

redetermine a final intraocular lens power based on the formula and the adjusted lens selection parameter.

18. An apparatus for intraocular lens selection, comprising:

a biometer configured to obtain at least two ocular measurement parameters for an eye;

a user interface configured to obtain a lens selection parameter for the eye;

an autorefractor configured to obtain a post-operative refraction of the eye;

a memory; and

a processor communicatively coupled to the biometer, the user interface, the autorefractor, and the memory, and configured to:

determine an intraocular lens power based on a formula using the at least two ocular measurement parameters;

correlate the at least two ocular measurement parameters, the intraocular lens power, and the post-operative refraction as a training set; and

transmit the training set to a network service configured to train a deep learning machine using the at least two ocular measurement parameters, the post-operative refraction of the eye, and the intraocular lens power of a plurality of training sets to determine an estimated error of the formula applied to at least two ocular measurement parameters of an eye of a new patient.

19. The apparatus of claim 18 , wherein the deep learning machine is trained with verified results exclusively from a particular lens manufacturer.

20. The apparatus of claim 18 , wherein the deep learning machine is a neural network configured to receive multiple numeric inputs to predict the estimated error of the formula as a single numeric output.

21. A method of intraocular lens selection, comprising:

obtaining at least two ocular measurement parameters for an eye by a biometer;

obtaining a lens selection parameter for the eye;

determining an intraocular lens power based on a formula using the at least two ocular measurement parameters;

obtaining a post-operative refraction of the eye from an autorefractor communicatively coupled with the biometer;

correlating the at least two ocular measurement parameters, the intraocular lens power, and the post-operative refraction as a training set; and

transmitting the training set to a network service configured to train a deep learning machine using the at least two ocular measurement parameters, the post-operative refraction of the eye, and the intraocular lens power of a plurality of training sets to determine an estimated error of the formula applied to at least two ocular measurement parameters of an eye of a new patient.

22. A non-transitory computer-readable medium storing computer executable instructions, comprising instructions to cause a computer to:

obtain at least two ocular measurement parameters for an eye by a biometer;

obtain a lens selection parameter for the eye;

determine an intraocular lens power based on a formula using the at least two ocular measurement parameters;

obtain a post-operative refraction of the eye from an autorefractor communicatively coupled with the biometer;

correlate the at least two ocular measurement parameters, the intraocular lens power, and the post-operative refraction as a training set; and

transmit the training set to a network service configured to train a deep learning machine using the at least two ocular measurement parameters, the post-operative refraction of the eye, and the intraocular lens power of a plurality of training sets to determine an estimated error of the formula applied to at least two ocular measurement parameters of an eye of a new patient.

Assignments (1)

Continuity (2)

References Cited (10)