X-ray image feature detection and registration systems and methods

Patent metadata

Field	Value
Publication number	US-10172582-B2
Application number	US-201615356013-A
Country	US
Kind code	B2
Filing date	Nov 18, 2016
Priority date	Nov 18, 2015
Publication date	Jan 8, 2019
Grant date	Jan 8, 2019

Abstract

The disclosure relates generally to the field of vascular system and peripheral vascular system data collection, imaging, image processing and feature detection relating thereto. In part, the disclosure more specifically relates to methods for detecting position and size of contrast cloud in an x-ray image including with respect to a sequence of x-ray images during intravascular imaging. Methods of detecting and extracting metallic wires from x-ray images are also described herein such as guidewires used in coronary procedures. Further, methods for of registering vascular trees for one or more images, such as in sequences of x-ray images, are disclosed. In part, the disclosure relates to processing, tracking and registering angiography images and elements in such images. The registration can be performed relative to images from an intravascular imaging modality such as, for example, optical coherence tomography (OCT) or intravascular ultrasound (IVUS).

First claim

What is claimed is:

1. A processor-based method of detecting one or more regions of interest in one or more x-ray images, the method comprising:
storing a set of angiography image frames of a subject obtained during a first time period in an electronic memory device of a processor-based diagnostic system, wherein the angiography image frames comprise x-ray imaged regions of blood vessels of the subject;
generating a plurality of centerlines, using the diagnostic system, from the imaged regions of blood vessels;
generating a binary image, using the diagnostic system, for a plurality of angiography image frames of the set for which centerlines has been generated;
generating a skeleton image frame, using the diagnostic system, for each angiography frame of the plurality of angiography image frames using the binary images of each such angiography frame and a centerline generated from blood vessel regions imaged in each such frame;
detecting, using the diagnostic system, one or more bifurcations on each frame of a group of skeleton image frames; and
performing interframe registration of angiography image frames using one or more detected bifurcations.

2. The method of claim 1 further comprising applying a rib filter or a temporal filter to a plurality of the skeleton image frames.

3. The method of claim 2 further comprising detecting one or more bends or anchor points in the filtered skeleton image frames.

4. The method of claim 1 wherein detecting one or more bifurcations comprises generating a cluster comprising a set of detected bifurcations across a plurality of frames, wherein the cluster is indicative of the detected bifurcations being the same bifurcations being imaged at different times on different angiography frames.

5. The method of claim 4 further comprising generating a plurality of clusters, wherein each cluster is a single bifurcation extracted from a group of frames.

6. The method of claim 5 further comprising generating one or more distance measurements between two or more clusters.

7. The method of claim 6 wherein the distance metric is a Euclidean metric.

8. The method of claim 6 further comprising validating one or more detected bifurcation if the feature is present on two or more angiography image frames.

9. The method of claim 8 further comprising consolidating the clusters to generates a set of clusters each having a single representative from each frame of interest.

10. The method of claim 9 further comprising selecting one or more clusters.

11. The method of claim 9 wherein the clusters are selected based on a parameters selected from the group consisting of: arc-length standard deviation, normalized arc-length standard deviation, angle difference standard deviation, proximity to other clusters, average number of redundant anatomical feature records per frames, and average number of missing bifurcation records per frame.

12. The method of claim 1 further comprising applying a vessel crossing filter to the skeleton image frames.

13. The method of claim 1 further comprising consolidating the clusters to generates a set of clusters each having a single representative from each frame of interest; and selecting one or more clusters, using the diagnostic system, wherein the clusters are selected based on a parameter selected from the group consisting of: arc-length standard deviation, normalized arc-length standard deviation, angle difference standard deviation, proximity to other clusters, average number of redundant anatomical feature records per frames, and average number of missing bifurcation records per frame.

14. A processor-based method of detecting one or more regions of interest in one or more x-ray images, the method comprising:
storing a set of angiography image frames of a subject obtained during a first time period in an electronic memory device of a processor-based diagnostic system, wherein the angiography image frames comprise x-ray imaged regions of blood vessels of the subject;
generating a plurality of centerlines, using the diagnostic system, from the imaged regions of blood vessels;
generating a binary image, using the diagnostic system, for a plurality of angiography image frames of the set for which centerlines has been generated;
generating a skeleton image frame, using the diagnostic system, for each angiography frame of the plurality of angiography image frames using the binary images of each such angiography frame and a centerline generated from blood vessel regions imaged in each such frame;
detecting , using the diagnostic system, one or more bends or anchor points on each frame of a group of skeleton image frames; and
performing interframe registration of angiography image frames using one or more detected bends or anchor points.

15. The method of claim 14 wherein detecting one or more bends or anchor points comprises generating a cluster comprising a set of detected bends or anchor points across a plurality of frames, wherein the cluster is indicative of the detected bends or anchor points being same bends or anchor points imaged at different times on different angiography frames.

16. The method of claim 15 further comprising consolidating the clusters to generates a set of clusters each having a single representative from each frame of interest.

17. The method of claim 14 further comprising applying one or more filters to one or more frames to facilitate detecting one or more bends or anchor points.

Assignees

• Lightlab Imaging Inc

Inventors

• Dascal Lorina
• Winkler Itai

Classifications

• G06T2207/10101

  Optical tomography; Optical coherence tomography [OCT] · CPC title

• G06T2207/10116

  X-ray image · CPC title

• A61B5/0066

  Optical coherence imaging · CPC title

• G06T5/50

  using two or more images, e.g. averaging or subtraction · CPC title

• A61B6/504

  for diagnosis of blood vessels, e.g. by angiography · CPC title