Back to results
US 11,759,090 B2Granted
Image-based airway analysis and mapping
AssigneeAuris Health, Inc.
InventorsMenglong Ye, Ritwik Ummalaneni
Life of this patent
Estimating the term…
Abstract
Navigation of an instrument within a luminal network can include image-based airway analysis and mapping. Image-based airway analysis can include detecting one or more airways in an image captured within a luminal network and determining branching information indicative of how the current airway in which the image is captured branches into the detected “child” airways. Image-based airway mapping can include mapping the one or more detected airways to corresponding expected airways of the luminal network in the preoperative model.
Claims20
A method of navigating an instrument through a luminal network, the method comprising:
- capturing a plurality of images within the luminal network with an imaging device positioned on the instrument, the plurality of images comprising at least a first image captured at a first time and a second image captured at a second time subsequent to the first time;
- identifying two or more airways in the first image;
- identifying a first airway in the second image, wherein the first airway in the second image is different from the two or more airways in the first image;
- determining a degree of spatial overlap between a first set of one or more geometric shapes representative of the two or more airways in the first image and a second set of one or more geometric shapes representative of the first airway in the second image;
- accessing preoperative model data indicative of an expected count of airways corresponding to a location of the instrument during the second time;
- determining, based on the preoperative model data and the degree of spatial overlap, a mapping between the first airway in the second image and an airway in the preoperative model data;
- and
- causing, based at least in part on the mapping between the first airway in the second image and the airway in the preoperative model data, the instrument to move through the luminal network.
5 more elements
A non-transitory computer readable storage medium having stored thereon instructions that, when executed, cause a processor of a device to at least:
- capture a plurality of images within a luminal network with an imaging device positioned on an instrument, the plurality of images comprising at least a first image captured at a first time and a second image captured at a second time subsequent to the first time;
- identify two or more airways in the first image;
- identify a first airway in the second image, wherein the first airway in the second image is different from the two or more airways in the first image;
- determine a degree of spatial overlap between a first set of one or more geometric shapes representative of the two or more airways in the first image and a second set of one or more geometric shapes representative of the first airway in the second image;
- access preoperative model data indicative of an expected count of airways corresponding to a location of the instrument during the second time;
- determine, based on the preoperative model data and the degree of spatial overlap, a mapping between the first airway in the second image and an airway in the preoperative model data;
- and
- cause, based at least in part on the mapping between the first airway in the second image and the airway in the preoperative model data, the instrument to move through the luminal network.
5 more elements
A robotic surgical system for mapping one or more airways in a luminal network, the system comprising:
- an instrument having:
- an elongate body configured to be inserted into the luminal network, and an imaging device positioned on a distal portion of the elongate body;
- an instrument positioning device attached to the instrument, the instrument positioning device configured to move the instrument through the luminal network;
- at least one computer-readable memory having stored thereon executable instructions;
- and
- one or more processors in communication with the at least one computer-readable memory and configured to execute the instructions to cause the system to at least:
- capture a plurality of images within the luminal network with the imaging device positioned on the instrument, the plurality of images comprising at least a
- first image captured at a first time and a second image captured at a second time subsequent to the first time;
- identify two or more airways in the first image;
- identify a first airway in the second image, wherein the first airway in the second image is different from the two or more airways in the first image;
- determine a degree of spatial overlap between a first set of one or more geometric shapes representative of the two or more airways in the first image and a second set of one or more geometric shapes representative of the first airway in the second image;
- access preoperative model data indicative of an expected count of airways corresponding to a location of the instrument during the second time;
- determine, based on the preoperative model data and the degree of overlap, a mapping between the first airway in the second image and an airway in the preoperative model data;
- and
- cause, based at least in part on the mapping between the first airway in the second image and the airway in the preoperative model data, the instrument to move through the luminal network.
12 more elements
Dependencies are inferred from the claim text.