Autonomous Robotic Drilling System for Mice Cranial Window Creation

2024-06-20

IEEE Transactions on Automation Science and Engineering

AI Summary

To address the challenge of high morphological and thickness variability in mouse skulls—caused by strain, sex, and age—and the limitations of existing cranial window drilling systems (e.g., reliance on offline planning and inability to perform precise, autonomous surgery), this study proposes the first end-to-end autonomous bone-drilling system that operates without preoperative planning and incorporates real-time closed-loop feedback. Our method integrates high-resolution microscopic vision with six-axis force sensing, enabling a lightweight deep learning model to detect dural penetration in real time and trigger adaptive trajectory replanning for 8-mm circular craniotomy. Key contributions include: (1) the first demonstration of model-free, closed-loop autonomous skull drilling on live murine subjects; and (2) a novel multimodal fusion–driven online penetration detection mechanism. Ex vivo validation achieved a 70% success rate (14/20), mean procedure time of 9.3 minutes, and >92% penetration classification accuracy—significantly outperforming state-of-the-art vision-only approaches.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Models for Web evolution
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

Robotic assistance for experimental manipulation in the life sciences is expected to enable favorable outcomes, regardless of the skill of the scientist. Experimental specimens in the life sciences are subject to individual variability and hence require intricate algorithms for successful autonomous robotic control. As a use case, we are studying the cranial window creation in mice. This operation requires the removal of an 8-mm circular patch of the skull, which is approximately 300 um thick, but the shape and thickness of the mouse skull significantly varies depending on the strain of the mouse, sex, and age. In this work, we develop an autonomous robotic drilling system with no offline planning, consisting of a trajectory planner with execution-time feedback with drilling completion level recognition based on image and force information. In the experiments, we first evaluate the image-and-force-based drilling completion level recognition by comparing it with other state-of-the-art deep learning image processing methods and conduct an ablation study in eggshell drilling to evaluate the impact of each module on system performance. Finally, the system performance is further evaluated in postmortem mice, achieving a success rate of 70% (14/20 trials) with an average drilling time of 9.3 min.

Problem

• Developing autonomous robotic drilling for mouse cranial window creation
• Addressing individual skull variability across mouse strains and ages
• Creating real-time planning system using image and force feedback

Innovation

• Autonomous robotic drilling system with no offline planning
• Trajectory planner with real-time feedback during execution
• Drilling completion recognition using image and force data