Robot-assisted Transcranial Magnetic Stimulation (Robo-TMS): A Review

2025-07-06

AI Summary

Conventional transcranial magnetic stimulation (TMS) faces engineering bottlenecks—including target localization drift and heavy reliance on manual operation—that hinder long-term precise neuromodulation. This paper systematically reviews advances in robot-assisted TMS (Robo-TMS), focusing on four core technical domains: robotic hardware integration, calibration and registration, neuronavigation, and closed-loop control. Key innovations include markerless head-motion tracking, non-rigid image registration, learning-based individualized electric field modeling, synthetic MRI generation, multi-target sequential stimulation, and automated online calibration—integrating robotics, neuronavigation, adaptive control, medical image analysis, and machine learning to achieve high-precision closed-loop neuromodulation. The study identifies critical translational challenges: limited clinical applicability, operational complexity, and high system cost. It further proposes a systematic roadmap for engineering optimization and clinical implementation, bridging technical advancement with practical deployment requirements.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Adversarial Learning & Robustness
• Cognitive Modeling & Cognitive Systems: Applications

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Transcranial magnetic stimulation (TMS) is a non-invasive and safe brain stimulation procedure with growing applications in clinical treatments and neuroscience research. However, achieving precise stimulation over prolonged sessions poses significant challenges. By integrating advanced robotics with conventional TMS, robot-assisted TMS (Robo-TMS) has emerged as a promising solution to enhance efficacy and streamline procedures. Despite growing interest, a comprehensive review from an engineering perspective has been notably absent. This paper systematically examines four critical aspects of Robo-TMS: hardware and integration, calibration and registration, neuronavigation systems, and control systems. We review state-of-the-art technologies in each area, identify current limitations, and propose future research directions. Our findings suggest that broader clinical adoption of Robo-TMS is currently limited by unverified clinical applicability, high operational complexity, and substantial implementation costs. Emerging technologies, including marker-less tracking, non-rigid registration, learning-based electric field (E-field) modelling, individualised magnetic resonance imaging (MRI) generation, robot-assisted multi-locus TMS (Robo-mTMS), and automated calibration and registration, present promising pathways to address these challenges.

Problem

• Enhancing precision in prolonged TMS sessions
• Addressing lack of engineering-focused Robo-TMS reviews
• Overcoming clinical adoption barriers in Robo-TMS

Innovation

• Advanced robotics integrated with TMS
• Marker-less tracking and non-rigid registration
• Learning-based E-field modelling and MRI generation