Deep Imitation Learning for Automated Drop-In Gamma Probe Manipulation

TL;DR

This paper presents a deep imitation learning approach to automate gamma probe manipulation in prostate cancer surgery, aiming to assist surgeons by improving detection accuracy through simulation-trained vision-based control.

Contribution

It introduces a novel deep imitation learning workflow trained on simulation data for automated gamma probe manipulation in surgical procedures.

Findings

Successfully predicts next-step actions in simulated environment

Demonstrates potential for real-world hardware implementation

Enhances accuracy and ease of gamma probe control

Abstract

The increasing prevalence of prostate cancer has led to the widespread adoption of Robotic-Assisted Surgery (RAS) as a treatment option. Sentinel lymph node biopsy (SLNB) is a crucial component of prostate cancer surgery and requires accurate diagnostic evidence. This procedure can be improved by using a drop-in gamma probe, SENSEI system, to distinguish cancerous tissue from normal tissue. However, manual control of the probe using live gamma level display and audible feedback could be challenging for inexperienced surgeons, leading to the potential for missed detections. In this study, a deep imitation training workflow was proposed to automate the radioactive node detection procedure. The proposed training workflow uses simulation data to train an end-to-end vision-based gamma probe manipulation agent. The evaluation results showed that the proposed approach was capable to predict the next-step action and holds promise for further improvement and extension to a hardware setup.