Systems and methods for robotic bronchoscopy navigation
Inventors
Danna, Kyle Ross • Zhang, Jian • Hung, Carol Kayee • Shawver, Michael J. • Slawinski, Piotr Robert • Thompson, Hendrik • Abraha, Liya K.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12193640-B2
Publication Date
2025-01-14
Expiration Date
Abstract
A method is provided for auto registration for a robotic endoscopic apparatus. The method comprises: (a) generate a first transformation between an orientation of the robotic endoscopic apparatus and an orientation of a location sensor based at least in part on a first set of sensor data collected using the location sensor; (b) generating a second transformation between a coordinate frame of the robotic endoscopic apparatus and a coordinate frame of a model representing an anatomical luminal network based at least in part on the first transformation and a second set of sensor data; and (c) updating, based at least in part on a third set of sensor data, the second transformation using an updating algorithm.
Core Innovation
The invention provides a method and system for navigating a robotic endoscopic apparatus by generating a first transformation and a second transformation between coordinate frames associated with the robotic endoscopic apparatus and a model representing an anatomical luminal network. A first transformation is generated between an orientation of the robotic endoscopic apparatus and an orientation of a location sensor based at least in part on a first set of sensor data collected using the location sensor. A second transformation is generated between a coordinate frame of the robotic endoscopic apparatus and a coordinate frame of the model representing the anatomical luminal network based at least in part on the first transformation and a second set of sensor data.
The invention further updates the second transformation based at least in part on a third set of sensor data using an updating algorithm. The updating algorithm comprises a fast interval recalculation operation and a slow interval recalculation operation. In the fast interval recalculation operation, a first set of associations is calculated using a subset of data sampled from the third set of sensor data, and the first set of associations is combined with a second set of associations calculated for generating the second transformation.
The fast and slow interval recalculation framework supports continuous navigation by refining the relationship between the robotic endoscopic apparatus coordinate frame and the anatomical luminal network model coordinate frame as additional sensor data are collected. The disclosure includes calculating associations between EM space and CT space for auto-registration and enables optionally producing a point cloud from the combined associations. An auto-registration method with three phases is described using an association solver and efficient nearest-neighbor data structures.
Claims Coverage
The patent includes two independent claims: a method claim and a system claim. Across these independent claims, the inventive subject matter centers on generating a first transformation and a second transformation and updating the second transformation with a fast/slow interval updating algorithm that uses associations computed from sampled sensor data and combined with prior associations (3 main inventive features).
Generating first and second transformations for luminal network navigation
generate a first transformation between an orientation of the robotic endoscopic apparatus and an orientation of a location sensor based at least in part on a first set of sensor data collected using the location sensor; and generate a second transformation between a coordinate frame of the robotic endoscopic apparatus and a coordinate frame of a model representing an anatomical luminal network based at least in part on the first transformation and a second set of sensor data
Fast and slow interval updating of the second transformation using combined associations
update, based at least in part on a third set of sensor data, the second transformation using an updating algorithm comprising a fast interval recalculation operation and a slow interval recalculation operation; wherein the fast interval recalculation operation comprises (i) calculating a first set of associations using a subset of data sampled from the third set of sensor data and (ii) combining the first set of associations with a second set of associations calculated for generating the second transformation
Processor-executed transformation generation and updating in a navigation system
a system for navigating a robotic endoscopic apparatus comprising a location sensor coupled to the robotic endoscopic apparatus, and one or more processors in communication with the location sensor and the robotic endoscopic apparatus and configured to execute a set of instructions to cause the system to generate a first transformation, generate a second transformation, and update the second transformation using an updating algorithm comprising a fast interval recalculation operation and a slow interval recalculation operation
Both independent claims focus on auto-registration for robotic endoscopic navigation using two transformations and an updating algorithm with fast and slow interval recalculation, where fast updates compute associations from sampled sensor data and combine them with prior associations.
Stated Advantages
Minimizing user interaction.
Reducing registration time.
Improving accuracy.
Documented Applications
Robotic bronchoscopy navigation using an auto-registration/navigation framework based on sensor data and a CT-derived luminal-network model.
Interested in licensing this patent?