Efficient cardiac MR workflows based on automated planning from mDIXON surveys
First Claim
Patent Images
1. A system for planning cardiac MRI views, said system comprising:
- at least one processor programmed to;
utilize an mDixon protocol scan sequence;
receive one or more images including an object of interest acquired from the mDIXON protocol scan sequence wherein the one or more received images include a water image and a fat image of the object of interest;
determine a position and orientation of the object of interest from the one or more images including identify edges of the object of interest by detecting transitions in gradient magnitude in the received one or more images, wherein the transitions provide a segmentation of the object of interest which is refined with non-maximum suppression;
match a model of the object of interest to the position and orientation of the object of interest;
generate one or more views of the object of interest from the matching of the object of interest; and
display the one or more views of the object of interest on a display device.
1 Assignment
0 Petitions
Accused Products
Abstract
A system (10) for planning cardiac MRI views, said system (10) includes a planning device (16) which includes at least one processor (42) programmed to: receive one or more images (18) from an imaging device (12) acquired utilizing an mDIX-ON protocol, determine a position and orientation of an object of interest from the one or more images, transform a model of the object of interest such that is matches the object of interest with a generalized Hough transform, and generate one or more object of interest views from the matching of the object of interest, A display (48) displays the one or more object of interest views.
-
Citations
14 Claims
-
1. A system for planning cardiac MRI views, said system comprising:
-
at least one processor programmed to; utilize an mDixon protocol scan sequence; receive one or more images including an object of interest acquired from the mDIXON protocol scan sequence wherein the one or more received images include a water image and a fat image of the object of interest; determine a position and orientation of the object of interest from the one or more images including identify edges of the object of interest by detecting transitions in gradient magnitude in the received one or more images, wherein the transitions provide a segmentation of the object of interest which is refined with non-maximum suppression; match a model of the object of interest to the position and orientation of the object of interest; generate one or more views of the object of interest from the matching of the object of interest; and display the one or more views of the object of interest on a display device. - View Dependent Claims (2, 3, 4)
-
-
5. A method for planning cardiac MRI views, said method comprising:
-
utilizing an mDixon protocol scan sequence; receiving one or more images including an object of interest acquired from the mDIXON protocol scan sequence wherein the one or more received images include a water image and a fat image of the object of interest; determining a position and orientation of the object of interest from the one or more images including;
identifying edges of the object of interest by detecting transitions in gradient magnitude in the received one or more images, wherein the transitions provide a segmentation of the object of interest which is refined with non-maximum suppression;matching a model of the object of interest to the position and orientation of the object of interest; generating one or more object of interest views from the matching of the object of interest; and displaying the one or more object of interest views on a display device. - View Dependent Claims (6, 7, 8, 9, 10, 11)
-
-
12. A system for planning cardiac MRI views, said system comprising:
-
a planning device which includes at least one processor programmed to; receive one or more images from an imaging device acquired in a single breath hold utilizing a cardiac gated mDIXON protocol wherein the one or more received images include a water image and a fat image of the object of interest; determine a position and orientation of an object of interest from the one or more images including identifying edges of the object of interest by detecting transitions in gradient magnitude in the received one or more images, wherein the transitions provide a segmentation of the object of interest which is refined with non-maximum suppression; transform a model of the object of interest such that is matches the object of interest using a generalized Hough transform; generate one or more cardiac views from the matching of the object of interest; and
a display which displays the one or more cardiac views. - View Dependent Claims (13, 14)
-
Specification