Volumetric filter of fluoroscopic sweep video
AssigneeCovidien LP
InventorsAriel Birenbaum, Shaked Pessah, Guy Alexandroni
Life of this patent
Estimating the term…
Abstract
Object detection including receiving a fluoroscopic video including a plurality of fluoroscopic images captured by a fluoroscope rotated about a patient, generating a three-dimensional (3D) volumetric reconstruction from the fluoroscopic images, deleting values in the 3D volumetric reconstruction beyond a region of interest about an object, generating 2D images from a remaining 3D volumetric reconstruction following the deleting of values: detecting the object in the 2D images to determine an initial position of the object, and refining the detected initial position of the object.
Claims20
A method of object detection comprising:
- receiving a fluoroscopic video including a plurality of fluoroscopic images captured by a fluoroscope rotated about a patient;
- generating a three-dimensional (3D) volumetric reconstruction from the received plurality of fluoroscopic images
- deleting values in the 3D volumetric reconstruction beyond a region of interest about an object;
- generating 2D images from a remaining 3D volumetric reconstruction following the deleting of values;
- detecting the object in the 2D images to determine an initial position of the object;
- and
- refining the detected initial position of the object.
A navigation system comprising:
- a transmitter mat configured to transmit an electromagnetic field;
- a catheter configured for navigation within a luminal network of patient, the catheter including a sensor proximate a distal tip;
- a computing device storing in a memory thereon an application that when executed by a processor causes the computing device to:
- receive a fluoroscopic video including a plurality of fluoroscopic images captured by a fluoroscope rotated about a patient;
- generate a three-dimensional (3D) volumetric reconstruction from the received plurality of fluoroscopic images;
- delete values in the 3D volumetric reconstruction beyond a region of interest about a detected position of the sensor;
- generate 2D images from a remaining 3D volumetric reconstruction following the deleting of values;
- detect the distal tip in the 2D images to determine an initial position of the distal tip;
- and
- refine the detected initial position of the distal tip of the catheter.
A method of testing accuracy of a fluoroscopic imaging device comprising:
- receiving a fluoroscopic video including a plurality of fluoroscopic images captured by a fluoroscope rotated about a test jig including a test marker at a known height;
- generating a three-dimensional (3D) volumetric reconstruction from the received plurality of fluoroscopic images;
- deleting values from the 3D volumetric reconstruction beyond a region of interest of the test marker;
- projecting a remaining 3D volumetric reconstruction to generate 2D images;
- detecting the test marker in the 2D images to determine an initial position of the test marker;
- and
- refining the determined initial position of the test marker.
Dependencies are inferred from the claim text.