A Supervised Autonomous Resection and Retraction Framework for Transurethral Enucleation of the Prostatic Median Lobe

TL;DR

This paper introduces a semi-autonomous robotic system for prostate tissue resection that combines model-based planning with learning-based retraction, achieving high resection accuracy in phantom experiments.

Contribution

It presents a novel coordinated framework integrating a resection planner and a learned retraction network for autonomous prostate enucleation using concentric tube robots.

Findings

Achieved 97.1% resection of targeted median lobe volume.

Demonstrated feasibility of supervised autonomous transurethral prostate resection.

Established a foundation for image-guided autonomous robotic surgery.

Abstract

Concentric tube robots (CTRs) offer dexterous motion at millimeter scales, enabling minimally invasive procedures through natural orifices. This work presents a coordinated model-based resection planner and learning-based retraction network that work together to enable semi-autonomous tissue resection using a dual-arm transurethral concentric tube robot (the Virtuoso). The resection planner operates directly on segmented CT volumes of prostate phantoms, automatically generating tool trajectories for a three-phase median lobe resection workflow: left/median trough resection, right/median trough resection, and median blunt dissection. The retraction network, PushCVAE, trained on surgeon demonstrations, generates retractions according to the procedural phase. The procedure is executed under Level-3 (supervised) autonomy on a prostate phantom composed of hydrogel materials that replicate the mechanical and cutting properties of tissue. As a feasibility study, we demonstrate that our combined autonomous system achieves a 97.1% resection of the targeted volume of the median lobe. Our study establishes a foundation for image-guided autonomy in transurethral robotic surgery and represents a first step toward fully automated minimally-invasive prostate enucleation.