Predictive Motion Mapping for Flexible Catheter Buckling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Minimally invasive procedures face challenges due to unexpected motion of tools, such as sideways translation and buckling, which are not perceptible in two-dimensional fluoroscopy, leading to potential adverse events like vessel dissection or perforation, especially when three-dimensional tool motion is not accurately modeled.
Innovation Solution
A predictive motion mapping system using artificial intelligence and robotic control to detect and predict unintended behavior of flexible medical devices by correlating proximal and distal end motions, providing warnings and guidance to prevent such events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If two-dimensional fluoroscopy is used for guidance, then the imaging system is simple and widely available, but three-dimensional tool motion cannot be accurately perceived leading to unexpected tool behavior
Solution Approach 1:
The system transitions from two-dimensional fluoroscopy imaging to three-dimensional motion tracking by incorporating multiple imaging planes and spatial coordinate systems. The tool centerline is represented in three-dimensional space with positional information along the entire length of the tool, not just at the distal end visible in fluoroscopy.
Solution Approach 2:
A predictive motion mapping system acts as an intermediary between the simple fluoroscopy system and the complex three-dimensional tool motion. The system uses trained artificial intelligence to predict three-dimensional tool behavior based on limited two-dimensional fluoroscopy input, effectively bridging the information gap.
2Productivity
If motion at the proximal end of the tool is increased to improve navigation efficiency, then procedural speed increases, but unexpected motion and buckling occur leading to safety risks
Solution Approach 1:
The system continuously monitors tool motion at the proximal end and provides real-time feedback predictions about the resulting distal end motion. When unexpected motion or buckling is predicted, the system can alert the operator to adjust their manipulation to maintain safe and predictable tool behavior.
Solution Approach 2:
The predictive motion mapping system performs preliminary analysis of potential tool responses before the operator completes their manipulation. By predicting the three-dimensional tool response to proximal end motion, the system allows operators to anticipate and prevent buckling or unintended behavior before it occurs.
3Device complexity
If conventional micro-catheter modeling with alternating straight-lines and curves is used, then the modeling process is simple, but interference from external forces such as physician manipulation is not accounted for
Solution Approach 1:
The system transitions from static geometric modeling (alternating straight-lines and curves) to dynamic motion prediction that accounts for external forces. The trained artificial intelligence models the time-varying response of the tool to physician manipulation and other external forces, capturing the dynamic nature of tool behavior during procedures.
Data Source
AI summary
A controller (150) for interventional medical devices includes a memory (151) and a processor (152). The memory (151) stores instructions that the processor (152) executes. When the instructions are executed, the instructions cause the controller (150) to obtain at least one location of a distal end of the interventional medical device (101), identify motion at a proximal end of an interventional medical device (101), apply a first trained artificial intelligence to the motion at the proximal end of the interventional medical device (101) and to the at least one location of the distal end of the interventional medical device (101), and predict motion along the interventional medical device (101) towards a distal end of the interventional medical device (101) during the interventional medical procedure. The controller (150) also obtains images of the distal end of the interventional medical device (101) from a medical imaging system (120) to determine when the actual motion deviates from the predicted motion.