Data-driven Holistic Framework for Automated Laparoscope Optimal View Control with Learning-based Depth Perception

TL;DR

This paper presents a data-driven, learning-based framework for automated laparoscope view control in minimally invasive surgery, integrating depth perception, tool segmentation, and distortion minimization to improve surgical assistance.

Contribution

It introduces a novel unsupervised depth estimation model and a control framework that combines learned motion strategies, real-time tool segmentation, and distortion correction for autonomous laparoscope positioning.

Findings

Framework successfully automates laparoscope control in experiments.

Depth estimation and tool segmentation achieve high accuracy.

Distortion minimization improves visual stability during surgery.

Abstract

Laparoscopic Field of View (FOV) control is one of the most fundamental and important components in Minimally Invasive Surgery (MIS), nevertheless, the traditional manual holding paradigm may easily bring fatigue to surgical assistants, and misunderstanding between surgeons also hinders assistants to provide a high-quality FOV. Targeting this problem, we here present a data-driven framework to realize an automated laparoscopic optimal FOV control. To achieve this goal, we offline learn a motion strategy of laparoscope relative to the surgeon's hand-held surgical tool from our in-house surgical videos, developing our control domain knowledge and an optimal view generator. To adjust the laparoscope online, we first adopt a learning-based method to segment the two-dimensional (2D) position of the surgical tool, and further leverage this outcome to obtain its scale-aware depth from dense depth estimation results calculated by our novel unsupervised RoboDepth model only with the monocular camera feedback, hence in return fusing the above real-time 3D position into our control loop. To eliminate the misorientation of FOV caused by Remote Center of Motion (RCM) constraints when moving the laparoscope, we propose a novel distortion constraint using an affine map to minimize the visual warping problem, and a null-space controller is also embedded into the framework to optimize all types of errors in a unified and decoupled manner. Experiments are conducted using Universal Robot (UR) and Karl Storz Laparoscope/Instruments, which prove the feasibility of our domain knowledge and learning enabled framework for automated camera control.