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-11403759-B2
Publication Date
2022-08-02
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 methods and apparatus described provide improved navigation through tubular networks such as lung airways by enhancing the estimation of the location and orientation information of a medical instrument, such as an endoscope, within the network. The system combines multiple types of input data—such as image data from the endoscope camera, electromagnetic (EM) sensor data, and robot data from the control platform—using distinct algorithm modules to estimate the state of the medical instrument in real time. This estimated state includes information like position, orientation, branch location, and depth within the network.
The system employs a navigation configuration framework that utilizes various algorithms, including EM-based, image-based, and robot-based algorithms, to generate state estimations and navigation data. Each algorithm can associate its estimations with probability distributions and confidence values, reflecting both the likelihood and reliability of possible instrument positions. These probabilistic estimations are combined to determine the instrument's most probable position and to guide navigation through the network towards a user-selected target site. The use of probability distributions and confidence values allows for dynamic adjustment and error correction during navigation.
The system also supports integrated pre-operative preparation steps, such as generating a 3D model of the network from CT scans, selecting a target site, and automatically planning a navigation path to the target. During the actual procedure, real-time data from multiple input sources and the generated 3D model are repeatedly analyzed to assist in guiding the instrument effectively within the tubular network, supporting both straightforward navigation and error correction as needed.
Claims Coverage
The patent contains three independent claims, each introducing distinctive inventive features related to estimation of instrument position within a tubular network using multimodal input data and confidence-weighted state estimation.
Multimodal state estimation and display for instrument navigation
A method involving: - Displaying a model of a patient's bronchial network. - Accessing both robotic data (including insertion data about a medical instrument) and sensor data from a sensor located at or near the tip of the instrument. - Determining two separate estimated states for the instrument: one based on the robot data, one on the sensor data. - Associating the sensor-based estimated state with a confidence value. - Determining the instrument's position by weighting the robot-based and sensor-based estimated states based on the confidence value. - Displaying the determined position of the instrument relative to the displayed bronchial model.
Robotic medical system for bronchoscopy with confidence-weighted position estimation
A robotic medical system comprising: - A robotically-controllable bronchoscope with an articulable distal end and a sensor, suitable for insertion into the bronchial network. - A display for rendering a model of the bronchial network. - At least one processor programmed to: - Access robotic data, including insertion data for the bronchoscope. - Access sensor data from the bronchoscope sensor. - Determine a robot-based estimated state and a sensor-based estimated state for the bronchoscope, with the latter associated with a confidence value. - Use the confidence value to determine instrument position, weighting towards the robot-based state as needed. - Display the bronchoscope position relative to the displayed bronchial model.
Robotic system with instrument device manipulator and confidence-driven navigation display
A robotic medical system including: - An instrument device manipulator compatible with a bronchoscope having an articulable end and a sensor. - A display. - At least one processor configured to: - Render a bronchial network model on the display. - Access robotic insertion data and bronchoscope sensor data. - Determine both robot-based and sensor-based estimated states for the bronchoscope, the latter associated with confidence value. - Determine instrument position at least weighted towards the robot-based state based on the confidence value. - Display this position on the model.
The inventive features provide a multimodal approach for instrument navigation in bronchial networks, combining robotic, sensor, and image data, weighing estimations by confidence, and displaying instrument position relative to a patient-specific 3D model for accurate and adaptive navigation.
Stated Advantages
Provides improved estimation of location and orientation information of a medical instrument within a tubular network, yielding more accurate and real-time localization.
Enables convenient navigation to specific target sites within complex branched networks by combining data from multiple sources and applying probability distributions and confidence values.
Allows dynamic adjustment and error correction during navigation through the use of confidence-weighted algorithm outputs.
Supports pre-operative planning and intra-operative navigation using patient-specific 3D models derived from CT scans.
Facilitates more convenient and effective operations for the physician by integrating real-time input data with model-based guidance.
Documented Applications
Navigation of medical instruments, such as endoscopes and bronchoscopes, through lung airways and other tubular anatomical networks for diagnostic and therapeutic procedures.
Robotic bronchoscopy for examination, therapy, and biopsy within the bronchial network of a patient.
Pre-operative planning and simulation of navigation paths in tubular networks using CT-derived 3D models.
Intra-operative real-time guidance and correction for medical instruments during minimally invasive procedures in tubular anatomical structures.
Interested in licensing this patent?