Learning-Based Modeling of a Magnetically Steerable Soft Suction Device for Endoscopic Endonasal Interventions

2025-07-20

AI Summary

Accurate modeling of large nonlinear deformations in magnetically actuated soft suction devices for endoscopic transnasal brain tumor resection remains challenging. Method: This paper proposes a physics-free, data-driven modeling paradigm integrating biocompatible 3D-printed soft structures, embedded fiber Bragg grating (FBG) sensing, Bezier-curve-based geometric representation, and a hybrid random forest–neural network learning framework to achieve end-to-end mapping from magnetic field inputs to deformation outputs. Results: Compared with conventional hyperelasticity-based simplified models, the proposed approach achieves significantly higher accuracy and generalizability: control-point prediction RMSE = 0.087 mm; 3D shape reconstruction error = 0.064 mm; enabling sub-millimeter real-time perception and closed-loop control. Contribution: This work pioneers high-fidelity learned modeling for clinical magnetic soft robots, establishing a verifiable and deployable foundation for intelligent deformation regulation in minimally invasive neurosurgery.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Bio-inspired Learning
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

This letter introduces a novel learning-based modeling framework for a magnetically steerable soft suction device designed for endoscopic endonasal brain tumor resection. The device is miniaturized (4 mm outer diameter, 2 mm inner diameter, 40 mm length), 3D printed using biocompatible SIL 30 material, and integrates embedded Fiber Bragg Grating (FBG) sensors for real-time shape feedback. Shape reconstruction is represented using four Bezier control points, enabling a compact and smooth model of the device's deformation. A data-driven model was trained on 5,097 experimental samples covering a range of magnetic field magnitudes (0-14 mT), actuation frequencies (0.2-1.0 Hz), and vertical tip distances (90-100 mm), using both Neural Network (NN) and Random Forest (RF) architectures. The RF model outperformed the NN across all metrics, achieving a mean root mean square error of 0.087 mm in control point prediction and a mean shape reconstruction error of 0.064 mm. Feature importance analysis further revealed that magnetic field components predominantly influence distal control points, while frequency and distance affect the base configuration. This learning-based approach effectively models the complex nonlinear behavior of hyperelastic soft robots under magnetic actuation without relying on simplified physical assumptions. By enabling sub-millimeter shape prediction accuracy and real-time inference, this work represents an advancement toward the intelligent control of magnetically actuated soft robotic tools in minimally invasive neurosurgery.

Problem

• Modeling magnetically steerable soft suction device for brain tumor resection
• Achieving sub-millimeter shape prediction accuracy in real-time
• Understanding nonlinear behavior of hyperelastic soft robots under magnetic actuation

Innovation

• Magnetically steerable soft suction device
• Learning-based modeling with FBG sensors
• Random Forest outperforms Neural Network