Automatic fundus image capture system

Patent metadata

Field	Value
Publication number	US-10758119-B2
Application number	US-201816158714-A
Country	US
Kind code	B2
Filing date	Oct 12, 2018
Priority date	Jul 24, 2015
Publication date	Sep 1, 2020
Grant date	Sep 1, 2020

Abstract

A system automatically captures a fundus image with limited user interaction such that the fundus image has one or more desired characteristics. The system can retrieve at least one image from an image capture device, process the at least one image digitally to generate a processed image, detect at least one point of interest in the processed image, determine that each of the at least one point of interest is representative of a corresponding feature of the eye, and obtain a fundus image of the eye based on the at least one image.

First claim

What is claimed is:

1. A method of automatically capturing a fundus image of an eye, the method comprising:
receiving at least one first image of the eye;
pre-processing, using at least one computing device, the at least one first image to generate a processed image;
detecting, using the at least one computing device, a point of interest in the processed image by identifying an area having an intensity different from surrounding areas of the processed image;
determining, with the at least one computing device, whether the point of interest is representative of a corresponding feature of the eye by determining whether a color ratio of the point of interest is within a predetermined value range;
when the color ratio is outside the predetermined value range, retrieving another image of the eye for analysis; and
obtaining the fundus image of the eye when the color ratio is within the predetermined value range such that the point of interest is the corresponding feature of the eye.

2. The method of claim 1 , further comprising retrieving a plurality of first images in a sequence.

3. The method of claim 2 , further comprising processing the plurality of first images to generate a plurality of processed images.

4. The method of claim 3 , further comprising detecting a point of interest in each of the plurality of processed images.

5. The method of claim 4 , further comprising:
comparing locations of the points of interest in each of the plurality of processed images; and
determining that the locations are substantially the same in each of the plurality of processed images.

6. The method of claim 4 , further comprising:
comparing sizes of the points of interest in each of the plurality of processed images; and
determining that the sizes are substantially the same in each of the plurality of processed images.

7. The method of claim 6 , further comprising:
determining if one of the plurality of processed images has a predetermined characteristic; and
if one of the plurality of processed images has the predetermined characteristic, saving that image as the fundus image.

8. The method of claim 1 , further comprising:
determining if the processed image has a predetermined characteristic;
if the processed image has the predetermined characteristic, saving the processed image as the fundus image.

9. The method of claim 8 , wherein the predetermined characteristic is associated with at least one of image quality and image size.

10. The method of claim 1 , further comprising displaying the fundus image through a display device.

11. An image capture device, comprising:
a processing device configured to control the image capture device; and
a computer readable data storage device storing software instructions that, when executed by the processing device, cause the image capture device to:
retrieve at least one first image from an image sensor device;
pre-process the at least one first image digitally to generate a processed image
detect at least one point of interest in the processed image by identifying an area having one or more solid circles in the processed image;
determine whether the at least one point of interest is representative of a corresponding feature of an eye, including to:
determine whether a color ratio of the point of interest is within a predetermined value range;
when the color ratio is outside the predetermined value range, retrieve another image of the eye for analysis; and

obtain a fundus image of the eye when the color ratio is within the predetermined value range such that the at least one point of interest is the corresponding feature.

12. The image capture device of claim 11 , wherein the software instructions cause the image capture device to retrieve a plurality of first images, the plurality of first images captured by the image sensor device in a sequence.

13. The image capture device of claim 12 , wherein the software instructions cause the image capture device to process the plurality of first images to generate a plurality of processed images.

14. The image capture device of claim 13 , wherein the software instructions cause the image capture device to detect a point of interest in each of the plurality of processed images.

15. The image capture device of claim 14 , wherein the software instructions cause the image capture device to compare locations of the points of interest in each of the plurality of processed images.

16. The image capture device of claim 15 , wherein the software instructions cause the image capture device to determine that the locations are substantially the same in each of the plurality of processed images.

17. The image capture device of claim 14 , wherein the software instructions cause the image capture device to:
compare sizes of the points of interest in each of the plurality of processed images; and
determine that the sizes are substantially the same in each of the plurality of processed images.

18. The image capture device of claim 12 , wherein the software instructions cause the image capture device to:
determine if one of the plurality of first images has a predetermined characteristic;
if one of the plurality of first images has the predetermined characteristic, save that image as the fundus image; and
if none of the plurality of first images has the predetermined characteristic, prompt the image sensor device to capture a second image and save the second image as the fundus image, the second image having the predetermined characteristic.

19. The image capture device of claim 18 , wherein the predetermined characteristic is associated with at least one of image quality and image size.

Assignees

• Welch Allyn Inc

Inventors

• Wang Ynjiun Paul
• Goldfain Ervin
• Lia Raymond A
• Maier David J
• Mudge Kenzi L
• Salvati Jon R

Classifications

• G06V40/193

  Preprocessing; Feature extraction · CPC title

• G06V40/19

  Sensors therefor · CPC title

• A61B3/12

  for looking at the eye fundus, e.g. ophthalmoscopes (A61B3/13 takes precedence) · CPC title

• A61B3/0025 Primary

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

• G06K9/0061

  Physics · mapped topic