System and method for classifying and quantifying age-related macular degeneration

Patent metadata

Field	Value
Publication number	US-10441159-B2
Application number	US-201615339146-A
Country	US
Kind code	B2
Filing date	Oct 31, 2016
Priority date	Oct 30, 2015
Publication date	Oct 15, 2019
Grant date	Oct 15, 2019

Abstract

The present disclosure describes a system and method to classify optical coherence tomography (OCT) images. The present system can classify OCT images without first segmenting the retina tissue. The system can generate one or more profiles from vertical transects through the OCT images. The system can identify image statistics based on the one or more profiles. The system's classifier can then classify the OCT images based on the identified image statistics.

First claim

What is claimed:

1. A system comprising one or more processors and a memory storing processor executable instructions, wherein execution of the instructions stored in the memory cause the one or more processors to:
retrieve, from the memory, an optical coherence tomography (OCT) image of retina tissue;
determine a location of a fovea in the OCT image;
identify a transect from the OCT image a predetermined distance from the location of the fovea, wherein the transect comprises an array of intensity values through the retina tissue of the OCT image;
generate a profile for the transect, the profile for the transect comprising at least one statistic of the array of intensity values; and
classify the OCT image using the profile for the transect into one of a wet age-related macular degeneration (AMD) group, a dry AMD group, or a healthy group.

2. The system of claim 1 , wherein execution of the instructions stored in the memory cause the one or more processor to preprocess the OCT image with at least one of down-sampling, de-noising, filtering, or flattening.

3. The system of claim 2 , wherein the wherein execution of the instructions stored in the memory cause the one or more processors to filter the OCT image with a Frangi filter.

4. The system of claim 1 , wherein execution of the instructions stored in the memory cause the one or more processors to:
identify an outline of the of the retina tissue;
calculate a derivative of the outline; and
determine a location of a minimum of the derivative.

5. The system of claim 1 , wherein execution of the instructions stored in the memory cause the one or more processors to extract a plurality of transects from the OCT image.

6. The system of claim 5 , wherein execution of the instructions stored in the memory cause the one or more processors to generate the profile responsive to each of the plurality of transects.

7. The system of claim 5 , wherein execution of the instructions stored in the memory cause the one or more processors to generate a respective profile for each of the plurality of transects.

8. The system of claim 1 , wherein execution of the instructions stored in the memory cause the one or more processors to determine a number of times the profile crosses at least one threshold.

9. The system of claim 1 , wherein execution of the instructions stored in the memory cause the one or more processors to classify the OCT image with at least one of a linear discriminant analysis (LDA), a k-nearest neighbor based algorithm, or a support vector machine.

10. A method comprising:
retrieving, from a memory, an optical coherence tomography (OCT) image of retina tissue;
determining a location of a fovea in the OCT image;
identifying a transect from the OCT image a predetermined distance from the location of the fovea, wherein the transect comprises an array of intensity values through the retina tissue of the OCT image;
generating a profile for the transect, the profile for the transect comprising at least one statistic of the array of intensity values; and
classifying the OCT image using the profile for the transect into one of a wet age-related macular degeneration (AMD) group, a dry AMD group, or a healthy group.

11. The method of claim 10 , further comprising preprocessing the OCT image with at least one of a down-sampling, a de-noising, a filtering, or a flattening algorithm.

12. The method of claim 11 , further comprising filtering the OCT image with a Frangi filter.

13. The method of claim 10 , further comprising:
identifying an outline of the of the retina tissue;
calculating a derivative of the outline; and
determining a location of a minimum of the derivative.

14. The method of claim 10 , further comprising extracting a plurality of transects from the OCT image.

15. The method of claim 14 , further comprising generating the profile responsive to each of the plurality of transects.

16. The method of claim 14 , further comprising generating a respective profile for each of the plurality of transects.

17. The method of claim 10 , further comprising determining a number of times the profile crosses at least one threshold.

18. The method of claim 10 , further comprising classifying the OCT image with at least one of a linear discriminant analysis (LDA), a k-nearest neighbor based algorithm, or a support vector machine.

Assignees

• Charles Stark Draper Laboratory Inc

Inventors

• Irvine John M
• Wood Richard
• Lowry Nathan
• Floyd David

Classifications

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06F18/2451

  linear, e.g. hyperplane · CPC title

• A61B3/0025 Primary

  characterised by electronic signal processing, e.g. eye models · CPC title

• G06T2207/20076

  Probabilistic image processing · CPC title

• G06T7/0012

  Biomedical image inspection · CPC title