System and method for sweep trajectory guidance
Inventors
Barve, Rakesh • Abrol, Sidharth • Chennamsetty, Sai Saketh • Subramany, Suthirth Vaidya • Chunduru, Abhijith
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12521086-B1
Publication Date
2026-01-13
Expiration Date
Abstract
A system for sweep trajectory guidance may include a catheter coupled to at least a transducer, wherein the at least a transducer is configured to receive ultrasound data, at least a localization system configured to detect probe position data as a function of a location of the catheter, at least a processor communicatively connected to the transducer, and a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to receive, by the at least a processor, the ultrasound data and the probe position data, generate, using a trained sweep trajectory simulation model, a movement vector as a function of the ultrasound data and the probe position data, determine, using the movement vector, real-time guidance data, and display the real-time guidance data to a user through at least a user interface.
Core Innovation
The invention is a catheter-based sweep trajectory guidance system and method. A catheter-coupled transducer receives ultrasound data, while a localization system detects probe position data based on catheter location. A sweep trajectory simulation model trained with reinforcement learning correlates the ultrasound and probe position data to generate a movement vector. The system uses the movement vector to determine real-time guidance data for display to a user.
The real-time guidance includes visual, auditory, or haptic prompts, target-proximity indicators, performance metrics, and catheter position relative to an ultrasound-derived three-dimensional anatomical model. The system continuously determines guidance updates in response to changes in ultrasound data and probe position data. In addition, computed tomography data provides training data for the reinforcement learning simulation model.
Claims Coverage
The claim coverage comprises five inventive features based on two independent claims directed to a catheter-based sweep trajectory guidance system and method.
Catheter-based sweep trajectory guidance system
A catheter coupled to at least a transducer receives ultrasound data, while a localization system detects probe position data based on catheter location. A processor uses a sweep trajectory simulation model trained with reinforcement learning to generate a movement vector from the ultrasound data and probe position data, determines real-time guidance data from the movement vector, and displays the guidance through a user interface.
Method for sweep trajectory guidance
The method receives ultrasound data from a transducer and detects probe position data using a localization system based on the location of a catheter coupled to the transducer. A processor uses a reinforcement-learning-trained sweep trajectory simulation model to correlate the ultrasound and probe position data with a movement vector, determines real-time guidance data using that vector, and displays the guidance to a user through a user interface.
Performance metric and continuous guidance updates
Determining a performance metric by comparing user actions with predicted optimal movement, displaying the metric in real time, and continuously updating real-time guidance data in response to changes in ultrasound data and probe position data.
Target proximity and three-dimensional position display
Providing visual indicators of catheter proximity to a target area and generating a 3D model of a target region from ultrasound data to display catheter position relative to the model using probe position data.
Specified model and input data sources
Using computed tomography data as training data for the reinforcement learning model and receiving ultrasound data and probe position data from an ultrasonic procedure.
The two independent claims cover system and method implementations that use ultrasound and catheter-related probe position data with a reinforcement-learning-trained sweep trajectory simulation model to generate movement vectors and provide real-time guidance, with dependent claims refining guidance outputs, position displays, and training sources.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Catheter-based sweep trajectory guidance using ultrasound data and catheter-related probe position data, including intracardiac echocardiography (ICE) and transesophageal echocardiography (TEE), with applications involving 2D TEE measurements, computed-tomography-derived left atrial appendage (LAA) dimensions, positioning a catheter in cardiac anatomy, and providing a real-time guidance interface.
Interested in licensing this patent?