Real-Time Robotic Needle Insertion in Deformable and Moving Structure Using Learning-By-Example Method
Thuc Long Ha, Julien Bert, Hadrien Courtecuisse
AI summary
Problem
Tissue deformation and motion during needle insertion make real-time path prediction difficult, while accurate inverse finite element simulations are too computationally heavy for real-time robotic control.
Approach
The authors train neural networks on data from offline inverse finite element simulations to learn the direct mapping between tissue-needle interactions and required robot displacements, shifting intensive calculations offline for instant online prediction.
Key results
- Successful prediction of steering commands via trained MLP and Residual FCN models
- Comparable or slightly better targeting accuracy in static and moving gel simulations
- Over 95% reduction in inverse computation time versus traditional finite element methods
- Validated needle steering in a reconstructed human body model with simulated respiration
Why it matters
Enables faster, more reliable real-time guidance for robotic needle-based medical procedures, reducing computational delays and improving clinical safety.
Abstract
This paper presents an innovative and practical method for robotic needle steering in radio-frequency ablation (RFA) to treat cancer. One of the main challenges in this process is that tissue shifts and deforms during needle insertion, making it difficult to accurately predict the needle’s path in real time. Inverse finite element (iFE) simulations have been used to address this problem. While these methods are accurate, they often require further refinement for effective time performance in real-world robotic systems. This is because when the method is incorporated into a real robot, there can be a delay in command execution. To address this challenge, we propose a machine learning-based solution that learns from offline simulations, shifting the intensive calculations required by iFE methods to an offline training stage and enabling online prediction of tissue deformation with reduced computational time. Our network was trained on data from numerous simu- lated needle insertions to capture interactions among insertion forces, tissue properties, and resulting motion. Once trained, the model produces predictions almost instantaneously, making it suitable for real-time applications. We validated the approach by steering the needle in a simulated deformable, moving gel to compare it with numerical-based methods, and then performing needle steering within a reconstructed human body that involves multiple structures and integrates the robot’s dynamics. The results demonstrated that the developed networks achieved slightly better accuracy in the first scenario while also running faster, resulting in improved performance under the robot’s dynamics. These findings show that our method is a promising advancement toward real-time guidance systems for needle- based medical procedures.