Segmentation and identification of layered structures in images

Patent metadata

Field	Value
Publication number	US-9299155-B2
Application number	US-201414337215-A
Country	US
Kind code	B2
Filing date	Jul 21, 2014
Priority date	Jan 20, 2010
Publication date	Mar 29, 2016
Grant date	Mar 29, 2016

Abstract

Disclosed herein are systems and method for segmentation and identification of structured features in images. According to an aspect, a method may include representing an image as a graph of nodes connected together by edges. For example, the image may be an ocular image showing layered structures or other features of the retina. The method may also include adding, to the graph, nodes adjacent to nodes along first and second sides of the graph. The added nodes may have edge weights less than the nodes along the first and second sides of the graph. Further, the method may include assigning start and end points to any of the added nodes along the first and second sides, respectively. The method may also include graph cutting between the start and end points for identifying a feature in the image.

First claim

What is claimed:

1. A method comprising:
representing an image as a graph of nodes connected together by edges, wherein the image includes first and second layered features;
identifying nodes corresponding to first and second layered features;
determining intensities of pixels of the image; and
determining positions of nodes of the graph corresponding to other layered features based on the determined intensities of the pixels and the determined positions of nodes corresponding to the first and second layered features, and
wherein determining positions of nodes of the graph corresponding to other layered features comprises graph cutting the graph of nodes, wherein a search associated with the graph cutting is limited to a region of the graph that excludes the nodes corresponding to first and second layered features.

2. The method of claim 1 , wherein the layered features are retinal layer boundaries.

3. The method of claim 1 , wherein identifying nodes corresponding to first and second layered features comprises graph cutting the graph of nodes.

4. A computer-implemented system comprising:
at least one processor and memory configured to:
represent an image as a graph of nodes connected together by edges, wherein the image includes first and second layered features;
identify nodes corresponding to first and second layered features;
determine intensities of pixels of the image; and
determine positions of nodes of the graph corresponding to other layered features based on the determined intensities of the pixels and the determined positions of nodes corresponding to the first and second layered features, and
wherein the processor and memory are configured to graph cut the graph of nodes, wherein a search associated with the graph cutting is limited to a region of the graph that excludes the nodes corresponding to first and second layered features.

5. The system of claim 4 , wherein the processor and memory are configured to graph cut the graph of nodes.

Assignees

• Univ Duke

Inventors

• Farsiu Sina
• Chiu Stephanie J
• Toth Cynthia A
• Izatt Joseph A
• Li Xiao T
• Nicholas Peter Christopher

Classifications

• G06V10/26

  Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion · CPC title

• G06T7/0093

  Physics · mapped topic

• G06T7/0081 Primary

  Physics · mapped topic

• A61B5/0066

  Optical coherence imaging · CPC title

• A61B5/7203

  for noise prevention, reduction or removal · CPC title