Automatic stent detection

Patent metadata

Field	Value
Publication number	US-9852504-B2
Application number	US-201615094577-A
Country	US
Kind code	B2
Filing date	Apr 8, 2016
Priority date	Oct 5, 2012
Publication date	Dec 26, 2017
Grant date	Dec 26, 2017

Abstract

This invention relates generally to the detection of objects, such as stents, within intraluminal images using principal component analysis and/or regional covariance descriptors. In certain aspects, a training set of pre-defined intraluminal images known to contain an object is generated. The principal components of the training set can be calculated in order to form an object space. An unknown input intraluminal image can be obtained and projected onto the object space. From the projection, the object can be detected within the input intraluminal image. In another embodiment, a covariance matrix is formed for each pre-defined intraluminal image known to contain an object. An unknown input intraluminal image is obtained and a covariance matrix is computed for the input intraluminal image. The covariances of the input image and each image of the training set are compared in order to detect the presence of the object within the input intraluminal image.

First claim

What is claimed is:

1. A computer-readable, non-transitory medium storing software code representing instructions that when executed by a computing system cause the computing system to perform a method of detecting an object within an image, the method comprising:
obtaining pre-defined data associated with the object disposed in a body lumen;
computing principal components for the pre-defined data to create an object space for the object disposed in a body lumen, wherein the computing comprises determining a threshold error using the pre-defined data and the object space;
projecting an input image onto the object space, wherein the projecting comprises determining an input image error by a second comparison of the input image and the object space; and
detecting the object disposed in the body lumen in the input image based on the input image error and the threshold error.

2. The computer-readable, non-transitory medium of claim 1 , wherein an input image error less than the threshold error constitutes a positive detection of the object disposed in the body lumen in the input image.

3. The computer-readable, non-transitory medium of claim 1 , wherein the pre-defined images and input image are one-dimensional, two-dimensional, or three-dimensional.

4. The computer-readable, non-transitory medium of claim 1 , further comprising post-processing the input image.

5. The computer-readable, non-transitory medium of claim 4 , wherein the step of post-processing comprises removing false detections and highlighting detections of objects disposed in the body lumen.

6. The computer-readable, non-transitory medium of claim 1 , further comprising
performing the steps of generating, identifying, and projecting for at least one other object; and
detecting the at least one other object in the input image.

7. The computer-readable, non-transitory medium of claim 6 , wherein the step of detecting the at least one other object further comprises
calculating an error between the input image and the object space for the object disposed in the body lumen and between the input image and the object space for the at least one other object.

8. The computer-readable, non-transitory medium of claim 7 , further wherein a small error constitutes a positive detection for the corresponding object.

9. The computer-readable, non-transitory medium of claim 6 , wherein the pre-defined images and input image are one-dimensional, two-dimensional, or three-dimensional.

10. The computer-readable, non-transitory medium of claim 1 , wherein the body lumen is a vasculature lumen.

11. The computer-readable, non-transitory medium of claim 1 , wherein the object disposed in the body lumen is selected from the group consisting of a stent, a stent strut, a guidewire, and tissue.

12. A system for automatically detecting an object within an image, comprising:
a central processing unit (CPU); and
a storage device coupled to the CPU and having stored there information for configuring the CPU to:
obtain pre-defined data associated with an object disposed in the body lumen;
compute principal components for the pre-defined data to create an object space for the object disposed in the body lumen, wherein the computing comprises determining a threshold error using the pre-defined data and the object space; and
project an input data image onto the object space, wherein the projecting comprises determining an input image error by a second comparison of the input image and the object space;
detect the object disposed in the body lumen in the input image based on the input image error and the threshold error.

13. The system of claim 12 , wherein an input image error less than the threshold error constitutes a positive detection of the object disposed in the body lumen in the input image.

14. The system of claim 12 , wherein the pre-defined images and input image are one-dimensional, two-dimensional, or three-dimensional.

15. The system of claim 12 , further comprising post-processing the input image.

16. The system of claim 15 , wherein post-processing comprises removing false detections and highlighting detections of objects disposed in the body lumen.

17. A method for detecting an object in an intraluminal image, the method comprising the steps of:
obtaining pre-defined data associated with an object disposed in the body lumen;
computing principal components for the pre-defined data to create an object space for the object disposed in the body lumen, wherein the computing comprises determining a threshold error using the pre-defined data and the object space;
projecting an input image onto the object space, wherein the projecting comprises determining an input image error by a second comparison of the input image and the object space; and
detecting the object disposed in the body lumen in the input image based on the input image error and the threshold error.

18. The method of claim 17 , further comprising processing the input image.

19. The method of claim 18 , wherein said processing step processing comprises removing false detections and highlighting detections of objects disposed in the body lumen.

Assignees

• Volcano Corp

Inventors

• Begin Elizabeth
• Kemp Nathaniel J
• Sproul Jason
• Elmaanaoui Badr

Classifications

• A61B8/4416

  related to combined acquisition of different diagnostic modalities, e.g. combination of ultrasound and X-ray acquisitions · CPC title

• G16H50/30

  for calculating health indices; for individual health risk assessment · CPC title

• A61B8/0841

  for locating instruments · CPC title

• A61B5/0073

  by tomography, i.e. reconstruction of 3D images from 2D projections (A61B5/0066 takes precedence) · CPC title

• A61B34/20

  Surgical navigation systems; Devices for tracking or guiding surgical instruments, e.g. for frameless stereotaxis · CPC title