Bayesian Retraction Optimization for Tissue Attachment Mapping in Surgical Dissection

2026-07-21

AI Summary

This study addresses the challenge of automatically identifying tissue adhesion regions during surgical dissection to enable precise robotic cutting and alleviate surgeon shortages. The authors propose a probabilistic approach that obviates explicit tissue modeling by leveraging Sequential Bayesian Hilbert Mapping (SBHM) to fuse spatial data from multiple classifiers collected during tissue pulling. This framework dynamically updates adhesion probabilities and employs Bayesian Pulling Optimization (BRO) to actively select the most informative actions under safety constraints. Notably, this work introduces Bayesian uncertainty modeling to this task for the first time, achieving zero-shot transfer to a real robotic system. Experiments demonstrate robust performance across diverse tissue geometries and data collection strategies in simulation, with successful validation on physical robotic dissection tasks.

Abstract

With growing surgeon shortages, automating surgical sub-tasks such as tissue dissection offers a promising step toward reducing workload and expanding patient access. Prior work has relied on hand-crafted incision policies that cannot quantify uncertainty or has relied on simulation-based methods that require strong modeling assumptions. We instead view tissue attachment identification as an inherently probabilistic problem and propose a Bayesian approach that avoids explicit tissue modeling. Our method uses a Sequential Bayesian Hilbert Map (SBHM) to represent the likelihood that each tissue point is attached to the underlying resection surface. An ensemble of learned classifiers predicts attachment likelihoods from spatial data acquired during robotic tissue retraction, with each classifier serving as a noisy information source to update the SBHM. To plan the next retraction, we devise Bayesian Retraction Optimization (BRO) to select the most informative action under safety constraints. As the SBHM refines over time, regions with high attachment likelihood are selectively incised. We validate our method in simulation across diverse tissue geometries and acquisition strategies, and demonstrate zero-shot transfer to real robotic dissection experiments.

Problem

• tissue attachment mapping
• surgical dissection
• Bayesian optimization
• robotic retraction
• uncertainty quantification

Innovation

• Bayesian Retraction Optimization
• Sequential Bayesian Hilbert Map
• tissue attachment mapping
• robotic dissection
• uncertainty quantification