Navigation of tubular networks
Inventors
Mintz, David S. • Ghoreyshi, Atiyeh • Jeevan, Prasanth • Xu, Yiliang • Yang, Gehua • Leotta, Matthew Joseph • Stewart, Charles V.
Assignees
Auris Health Inc • Kitware Inc
Publication Number
US-9727963-B2
Publication Date
2017-08-08
Expiration Date
2036-09-16
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
Methods and apparatuses provide improved navigation through tubular networks such as lung airways by providing improved estimation of location and orientation information of a medical instrument (e.g., an endoscope) within the tubular network. Various input data such as image data, EM data, and robot data are used by different algorithms to estimate the state of the medical instrument, and the state information is used to locate a specific site within a tubular network and/or to determine navigation information for what positions/orientations the medical instrument should travel through to arrive at the specific site. Probability distributions together with confidence values are generated corresponding to different algorithms are used to determine the medical instrument's estimated state.
Core Innovation
The invention provides methods and apparatuses for improved navigation of medical instruments, such as endoscopes, through tubular networks like lung airways by enhancing the estimation of location and orientation of the instrument within the network. The invention achieves this by integrating various input data including image data, electromagnetic (EM) data, and robotic data, which are processed by different algorithms to estimate the state of the medical instrument in real time.
The need for this invention arises from challenges in accurately determining the real-time location and orientation of a medical device inside a patient’s tubular anatomy using conventional techniques. Traditional methods based on device location and orientation changes may lack sufficient accuracy, resulting in potential mislocalization of the device, which can mislead clinicians during procedures relying on models or image guidance.
The disclosed system comprises a navigation configuration system equipped with multiple algorithm modules, each generating its own state estimation and associated probability distributions with confidence values. By combining output from EM-based, image-based, and robot-based algorithms, the system generates a composite estimated state for the instrument, enabling precise localization and pathway determination within the tubular network. This estimation is further used to guide the instrument to specific sites and plan navigation paths, supporting both pre-operative planning and intraoperative guidance.
Claims Coverage
The patent claims cover a method and apparatus for estimating the state of a medical instrument within a patient’s tubular network using a combination of robotic, image, and electromagnetic data, each processed with associated confidence values, and generating a composite state estimate for navigation purposes. The independent claim sets forth the core inventive features as follows:
Composite state estimation from robot, image, and electromagnetic data with confidence values
The method involves: - Accessing robotic data relating to physical manipulation of an elongated medical instrument within a tubular network. - Accessing image data from an imaging device near the instrument tip. - Accessing electromagnetic (EM) data from an EM sensor near the tip, including data from an external EM sensor or generator. - Determining a robot-based estimated state for the instrument tip with an associated confidence value. - Determining an image-based estimated state with its own confidence value. - Determining an EM-based estimated state and corresponding confidence value. - Combining the robot-based, image-based, and EM-based estimated states and respective confidence values to generate a final estimated state for the instrument tip.
Flexible endoscope structure controlled by an instrument device manipulator
The elongated medical instrument can be a flexible endoscope with an endolumenal structure and multiple cables that may be retracted or related to alter the direction of the instrument tip. The endoscope is manipulated by an instrument device manipulator (IDM) for insertion, withdrawal, and rolling within the tubular network.
Registration of electromagnetic system to 3D model for state estimation
Determining the EM-based estimated state comprises registering an EM system (including EM data coordinates) to a 3D model (with coordinates based on a 3D model of the tubular network). The EM-based estimated state is generated based on this registration, enabling position and orientation estimation relative to possible branches within the network.
Probability distribution and confidence-based combination of estimated states
Each of the robot-based, image-based, and EM-based estimated states can be represented as probability distributions over possible values, weighted by their respective confidence values. The combined estimated state is produced using these probability distributions and confidence values.
Navigation path planning and instruction based on estimated state
Based on the estimated state, the system can access a navigation path to a target location within the tubular network, determine navigation instructions to guide the instrument tip toward the target, and present these instructions to the operator.
In summary, the claims protect a method and system for estimating and navigating the location and orientation of medical instruments in tubular networks using a multi-data, multi-algorithm approach with confidence-weighted probabilities, as well as apparatus and methods for registration, control, and navigation guidance.
Stated Advantages
Provides improved estimation of location and orientation information of a medical instrument within a tubular network.
Enables more accurate real-time localization of medical instruments, addressing challenges in conventional techniques.
Combining probability distributions and confidence values from multiple algorithms enhances overall estimation accuracy.
Facilitates automatic navigation path planning and intraoperative guidance, allowing more convenient and effective operations by the physician.
Allows pre-operative planning with 3D models generated from patient scans, improving surgical preparation.
System can recover from errors by using multiple data sources and changing state estimations as more information becomes available.
Documented Applications
Navigation and localization of medical instruments such as robotic endoscopes during procedures in patient tubular networks, especially lung airways for bronchoscopy.
Pre-operative planning and virtual endoscopy for determining and practicing instrument navigation paths to a specific target (for example, a lesion for biopsy) in a branched tubular network.
Guidance and control of instruments for intraoperative tasks such as biopsies or surgical repair within tubular anatomical structures.
Interested in licensing this patent?