Navigation of tubular networks
Inventors
Mintz, David S. • Ghoreyshi, Atiyeh • Jeevan, Prasanth • Xu, Yiliang • Yang, Gehua • Leotta, Matthew Joseph • Stewart, Charles V.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12653374-B2
Publication Date
2026-06-16
Expiration Date
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 relates to navigating a tubular network, including lung airways, using a navigation configuration system that combines a preoperative tubular network model with robotic insertion data and distal-sensor data from an elongated medical instrument. A position and orientation of the elongated medical instrument relative to one or more branches of the tubular network are estimated so that the second estimated state comprises a probability distribution indicating a likelihood of the elongated medical instrument being inside each of the one or more branches.
The navigation configuration system estimates an instrument state in a multi-stage manner by determining a first estimated state based at least in part on insertion data, determining a second estimated state based at least in part on sensor data, determining a position of the elongated medical instrument relative to the model of the tubular network based at least in part on the second estimated state, and determining a third estimated state based at least in part on the first estimated state and the position of the elongated medical instrument relative to the model of the tubular network.
The system includes multiple algorithm modules that provide EM-based with on-the-fly EM-to-3D registration and branch selection, image-based object/motion/topological reasoning, and robot-based motion and uncertainty handling to estimate an instrument state as probability distributions with confidence values. Bayesian updates generate posterior probabilities, a registration transform is updated over time, and recovery from branch-estimation errors is performed by reconciling contradictory measurements, while pre-operative CT-derived 3D airway model generation and path planning with virtual endoscopy are described with user interfaces for guidance.
Claims Coverage
The partial content includes three independent claims (method claim 1, system claim 14, and bronchoscopy system claim 16). Across the independent claims, the core coverage is defined by five inventive features: model access, combined robotic insertion and distal sensor data access, multi-stage estimation of an instrument state including a branch probability distribution, determination of instrument position relative to the model, and determination of a third estimated state based on earlier estimated state and model-relative position.
Accessing a model of a tubular network
The method or system accesses a model of the tubular network.
Accessing robotic insertion data and distal sensor data
The method or system accesses robotic data including insertion data associated with robotic insertion into the tubular network and accesses sensor data derived from a sensor of the elongated medical instrument associated with a distal portion.
Multi-branch state estimation with a probability distribution over branches
The method or system determines a first estimated state based at least in part on the insertion data, and determines a second estimated state based at least in part on the sensor data by estimating a position and orientation of the elongated medical instrument relative to one or more branches, where the second estimated state comprises a probability distribution indicating a likelihood of the elongated medical instrument being inside each of the one or more branches.
Model-relative instrument position determination
The method or system determines a position of the elongated medical instrument relative to the model of the tubular network based at least in part on the second estimated state.
Third estimated state refinement using first estimated state and model-relative position
The method or system determines a third estimated state for the elongated medical instrument based at least in part on the first estimated state and the position of the elongated medical instrument relative to the model of the tubular network.
The independent claims are directed to a navigation approach where insertion data and distal sensor data are used to estimate instrument position and orientation relative to tubular network branches, producing a probability distribution over branch membership, then using model-relative position to refine a subsequent estimated state.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?