Towards Motion Compensation in Autonomous Robotic Subretinal Injections

2024-11-27

arXiv.org

AI Summary

In subretinal injection for wet age-related macular degeneration, physiological Z-axis micro-movements of the retina—induced by respiration and cardiac pulsation—significantly compromise targeting accuracy. To address this, we propose a real-time, closed-loop robotic motion compensation system leveraging optical coherence tomography (OCT). Our method employs high-speed, small-volume B⁵-scan OCT (>100 Hz) for real-time retinal Z-axis tracking and implements a dynamic prediction–feedback compensation framework. Ex vivo porcine eye experiments demonstrate effective suppression of Z-axis physiological motion (25–100 μm); however, residual horizontal drift causes 80–200 μm needle-tip targeting errors. This study is the first to reveal the critical role of horizontal stability and motion prediction in achieving precise subretinal injection. The results establish a novel paradigm and provide empirical validation for clinical-grade robotic ophthalmic surgery.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Exudative (wet) age-related macular degeneration (AMD) is a leading cause of vision loss in older adults, typically treated with intravitreal injections. Emerging therapies, such as subretinal injections of stem cells, gene therapy, small molecules or RPE cells require precise delivery to avoid damaging delicate retinal structures. Autonomous robotic systems can potentially offer the necessary precision for these procedures. This paper presents a novel approach for motion compensation in robotic subretinal injections, utilizing real-time Optical Coherence Tomography (OCT). The proposed method leverages B$^{5}$-scans, a rapid acquisition of small-volume OCT data, for dynamic tracking of retinal motion along the Z-axis, compensating for physiological movements such as breathing and heartbeat. Validation experiments on extit{ex vivo} porcine eyes revealed challenges in maintaining a consistent tool-to-retina distance, with deviations of up to 200 $mu m$ for 100 $mu m$ amplitude motions and over 80 $mu m$ for 25 $mu m$ amplitude motions over one minute. Subretinal injections faced additional difficulties, with horizontal shifts causing the needle to move off-target and inject into the vitreous. These results highlight the need for improved motion prediction and horizontal stability to enhance the accuracy and safety of robotic subretinal procedures.

Problem

• Develops motion compensation for robotic subretinal injections.
• Addresses challenges in precise delivery to avoid retinal damage.
• Improves accuracy and safety using real-time OCT tracking.

Innovation

• Real-time OCT for retinal motion tracking
• B$^5$-scans for dynamic Z-axis compensation
• Enhanced precision in robotic subretinal injections