System and method for pose estimation of an imaging device and for determining the location of a medical device with respect to a target
AssigneeCovidien LP
InventorsRon Barak, Ariel Birenbaum, Guy Alexandroni, Oren P. Weingarten
Life of this patent
Estimating the term…
Abstract
A system and method for constructing fluoroscopic-based three-dimensional volumetric data of a target area within a patient from two-dimensional fluoroscopic images acquired via a fluoroscopic imaging device.
Claims20
A system for constructing three-dimensional volumetric data of a target area within a patient from two-dimensional (2D) images acquired via a rotatable imaging device, comprising:
- a structure of markers, wherein a sequence of 2D images of the target area and of the structure of markers is acquired via a rotatable imaging device;
- and
- a computing device configured to:
- detect a most probable projection of the structure of markers as a whole on each image of at least a portion of the sequence of 2D images;
- estimate a pose of the rotatable imaging device for the at least the portion of the sequence of 2D images based on the most probable projection of the structure of markers as a whole on each image of the at least the portion of the sequence 2D images, yielding estimated poses of the rotatable imaging device;
- construct three-dimensional volumetric data of the target area from the at least the portion of the sequence 2D images based on the respective estimated poses of the rotatable imaging device;
- determine a distance between a medical device and a target appearing in the three-dimensional volumetric data;
- and
- correct a display of the medical device with respect to the target based on the distance.
A method for constructing fluoroscopic-based three dimensional volumetric data of a target area within a patient from a sequence of two-dimensional (2D) images of a target area and of a structure of markers acquired via a rotatble imaging device, wherein the structure of markers is positioned between the patient and the rotatable imaging device, the method comprising using at least one hardware processor for:
- detecting a most probable projection of the structure of markers as a whole on each image of at least a portion of the sequence of 2D images acquired via the rotatble imaging device;
- estimating a pose of the rotatable imaging device for at least a portion of the sequence of 2D images based on the most probable projection of the structure of markers as a whole on each image of the at least the portion of the sequence of 2D images;
- constructing three-dimensional volumetric data of the target area from the at least the portion of the 2D images based on the respective estimated poses of the rotatable imaging device;
- determining a distance between a medical device and a target appearing in the three-dimensional volumetric data;
- and
- correcting a display of the medical device with respect to the target based on the distance.
A system for constructing three-dimensional volumetric data of a target area within a patient from two-dimensional (2D) images acquired via a rotatable imaging device, comprising:
- a computing device configured to:
- detect a most probable projection of a structure of markers as a whole on each image of at least a portion of a sequence of 2D images acquired via a rotatable imaging device;
- estimate a pose of the rotatable imaging device for the at least the portion of the sequence of 2D images based on the most probable projection of the structure of markers as a whole on each image of the at least the portion of the sequence of 2D images, yielding estimated poses of the rotatable imaging device;
- construct three-dimensional volumetric data of the target area from the at least the portion of the sequence of 2D images based on the respective estimated poses of the rotatable imaging device;
- determine a distance between a medical device and a target appearing in the three-dimensional volumetric data;
- and
- correct a display of the medical device with respect to the target based on the distance.
Dependencies are inferred from the claim text.