Hybrid registration method
First Claim
Patent Images
1. A method of registering an airway to a three-dimensional 3D model of the airway:
- acquiring a plurality of computed tomography (CT) images of the airways of a patient;
generating a 3D model of the airways derived from the plurality of CT images;
generating a plurality of virtual endoscopic images derived from the 3D model;
acquiring an endoscopic image;
comparing the endoscopic image to the plurality of virtual endoscopic images to identify a match between the endoscopic image and a virtual endoscopic image of the plurality of virtual endoscopic images, wherein a viewpoint of the matching virtual endoscopic image substantially corresponds to a viewpoint of the endoscopic image;
determining a position associated with an endoscope in an airway of a patient to form a determined position;
comparing the determined position with a location in the 3D model corresponding to the matching virtual endoscopic image; and
when the determined position and the location in the 3D model substantially correspond, depicting a location of the endoscope in the 3D model.
3 Assignments
0 Petitions
Accused Products
Abstract
A registration method whereby a sensor-based approach is used to establish initial registration and whereby upon the commencement of navigating an endoscope, image-based registration methods are used in order to more accurately maintain the registration between the endoscope location and previously-acquired images. A six-degree-of-freedom location sensor is placed on the probe in order to reduce the number of previously-acquired images that must be compared to a real-time image obtained from the endoscope.
-
Citations
19 Claims
-
1. A method of registering an airway to a three-dimensional 3D model of the airway:
-
acquiring a plurality of computed tomography (CT) images of the airways of a patient; generating a 3D model of the airways derived from the plurality of CT images; generating a plurality of virtual endoscopic images derived from the 3D model; acquiring an endoscopic image; comparing the endoscopic image to the plurality of virtual endoscopic images to identify a match between the endoscopic image and a virtual endoscopic image of the plurality of virtual endoscopic images, wherein a viewpoint of the matching virtual endoscopic image substantially corresponds to a viewpoint of the endoscopic image; determining a position associated with an endoscope in an airway of a patient to form a determined position; comparing the determined position with a location in the 3D model corresponding to the matching virtual endoscopic image; and when the determined position and the location in the 3D model substantially correspond, depicting a location of the endoscope in the 3D model. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A method of registering sensor location data to images of a patient'"'"'s at least one body part, comprising:
-
generating location data corresponding to a location of a sensor within a patient'"'"'s body by recording a shape of a segment of the patient'"'"'s at least one body part and identifying a segment in a 3D model, which is derived from computed tomography (CT) images, that corresponds to the shape of the recorded segment; comparing a plurality of previously acquired images of the patient'"'"'s at least one body part to a plurality of virtual images derived from the CT images to identify a subgroup of the plurality of previously acquired images of the patient'"'"'s at least one body part; registering the location of the sensor relative to the subgroup of the plurality of previously acquired images of the patient'"'"'s at least one body part based on the location data; and updating the registered location of the sensor based on one or more images selected from the subgroup. - View Dependent Claims (7, 8, 9, 10, 11, 12, 13)
-
-
14. A method of registering sensor location data to images of at least one body part, comprising:
-
generating location data corresponding to a location of a sensor within a patient'"'"'s body; comparing a plurality of previously acquired images of the patient'"'"'s at least one body part to a plurality of virtual images derived from computed tomography (CT) images to identify a subgroup of the plurality of previously acquired images of the patient'"'"'s at least one body part; registering the location of the sensor relative to the subgroup of the plurality of previously acquired images of the patient'"'"'s at least one body part based on the location data; updating the registered location of the sensor based on one or more images selected from the subgroup; and displaying the one or more images selected from the subgroup. - View Dependent Claims (15, 16, 17, 18, 19)
-
Specification