Back to results
US 12,733,999 B2Granted
Training system for a neural network to guide a robotic arm to operate a catheter
AssigneeBiosense Webster (Israel) Ltd.
InventorsAssaf Govari, Andres Claudio Altmann, Vadim Gliner
Life of this patent
Estimating the term…
Abstract
Methods and systems are provided for training machine learning (e.g., NN) or other artificial intelligence (AI) models to control a robot arm to manipulate a catheter to robotically perform an invasive clinical catheter-based procedure.
Claims16
A training system, comprising:
- one or more training setups, each training setup comprising:
- a catheter for insertion into a heart, the catheter comprising:
- multiple sensors located at a handpiece of the catheter, the sensors configured to sense manual operations of a physician performing a heart procedure using the catheter;
- and
- a distal sensor located at a distal end of the catheter and configured to indicate a position of the distal end inside the heart corresponding to the manual operations;
- and
- a processor, configured to:
- receive, from the one or more training setups, manual operations data acquired using the multiple sensors and the respective distal sensor of each training setup;
- and
- using the manual operations data, train a machine learning (ML) model to guide a robotic arm to operate the handpiece of the catheter, in an absence of concurrent manual operations of the physician, to perform the heart procedure.
7 more elements
A training method, comprising:
- in each of one or more training setups, inserting a catheter into a heart, the catheter comprising:
- multiple sensors located at a handpiece of the catheter, the sensors configured to sense manual operations of a physician performing a heart procedure using the catheter;
- and
- a distal sensor located at a distal end of the catheter and configured to indicate a position of the distal end inside the heart corresponding to the manual operations;
- receiving, from the one or more training setups, manual operations data acquired using the multiple sensors and the respective distal sensor of each training setup;
- and
- using the manual operations data, training a machine learning (ML) model to guide a robotic arm to operate the handpiece of the catheter, in an absence of concurrent manual operations of the physician, to perform the heart procedure.
4 more elements
Dependencies are inferred from the claim text.