Robotic system uses 3D scans to control soft tissue shapes precisely
Robotic Optical Coherence Tomography-Guided Geometric Modeling of Soft Tissue: 3D Representations for Data-Driven Closed-Loop Shape Control
Robotics
Summary
Controlling the shape of soft tissue during delicate medical procedures is tough because tiny movements are hard to see and model. The researchers developed a robotic system that uses detailed 3D scans from optical coherence tomography (OCT) to learn and control tissue shape changes in real time. Their approach combines different ways of representing the 3D tissue shape with machine learning controls, which helps the robot match desired tissue shapes accurately. They tested their system on fake and real tissue pieces and got results close to those achieved by human experts.
What this means in practice
- •For medical device engineers: Develop robotic surgical tools that use 3D OCT scans to shape soft tissue accurately during microsurgery.$Commercial implications: This paper enables new surgical robots offering precise tissue manipulation via OCT feedback, improving procedure safety and outcomes.
- •For biomedical robotics developers: Create adaptive control systems for robotic tissue manipulation that learn from user demonstrations and adjust in real time using OCT data.
Authors
Chaoyu Zhang, Guangshen Ma, Mark Draelos
Abstract
In medical robotics, data-driven soft-tissue shape control requires deforming tissue toward desired morphologies through sequential physical interactions. This challenge is particularly important in microscale manipulation, where localized deformation is difficult to observe, represent, and control, while physics-based models can be computationally expensive and difficult to adapt to realistic environments. Optical coherence tomography (OCT) provides high-resolution volumetric perception of tissue deformation, but target-conditioned control requires effective representations of both observed and desired tissue states. In this work, we introduce an OCT-guided data-driven framework for tissue shape control, learned from user-guided demonstrations and executed with closed-loop OCT feedback. We study full-volume, tissue-masked sparse-volume, and voxelized point-cloud representations, with or without residual conditioning, using deterministic (Explicit) and generative diffusion (Diffusion) policies. Across 12 configurations and 576 phantom rollouts on 3-DoF depth and 6-DoF directional tasks, OCT-derived 3D representations support both Explicit and Diffusion policies, with performance depending on representation and residual conditioning. Residual conditioning reduces directional Shape RMSE from 0.748 to 0.555 mm for full-volume Diffusion, while voxelized point-cloud Explicit with residuals achieves 0.534 mm for depth and 0.443 mm for directional control, with comparable accuracy at intermediate unseen targets and consistent performance across deployments. We further evaluate the framework in 60 ex vivo porcine rollouts, extending to biological tissue with final geometric errors comparable to human demonstrations. These results establish volumetric OCT as current and goal representations for learned closed-loop tissue shape control across deterministic and generative action models.