RESUMEN

Laser ablation is an effective treatment modality. However, current laser scanners suffer from laser defocusing when scanning targets at different depths in a 3D surgical scene. This study proposes a deep learning-assisted 3D laser steering strategy for minimally invasive surgery that eliminates laser defocusing, increases working distance, and extends scanning range. An optofluidic laser scanner is developed to conduct 3D laser steering. The optofluidic laser scanner has no mechanical moving components, enabling miniature size, lightweight, and low driving voltage. A deep learning-based monocular depth estimation method provides real-time target depth estimation so that the focal length of the laser scanner can be adjusted for laser focusing. Simulations and experiments indicate that the proposed method can significantly increase the working distance and maintain laser focusing while performing 2D laser steering, demonstrating the potential for application in minimally invasive surgery.

RESUMEN

In the robot-assisted minimally invasive surgery, if a collision occurs, the robot system program could be damaged, and normal tissues could be injured. To avoid collisions during surgery, a 3-dimensional collision avoidance method is proposed in this paper. The proposed method is predicated on the design of 3 strategic vectors: the collision-with-instrument-avoidance (CI) vector, the collision-with-tissues-avoidance (CT) vector, and the constrained-control (CC) vector. The CI vector demarcates 3 specific directions to forestall collision among the surgical instruments. The CT vector, on the other hand, comprises 2 components tailored to prevent inadvertent contact between the robot-controlled instrument and nontarget tissues. Meanwhile, the CC vector is introduced to guide the endpoint of the robot-controlled instrument toward the desired position, ensuring precision in its movements, in alignment with the surgical goals. Simulation results verify the proposed collision avoidance method for robot-assisted minimally invasive surgery. The code and data are available at https://github.com/cynerelee/collision-avoidance.

RESUMEN

OBJECTIVE: The computation of anatomical information and laparoscope position is a fundamental block of surgical navigation in Minimally Invasive Surgery (MIS). Recovering a dense 3D structure of surgical scene using visual cues remains a challenge, and the online laparoscopic tracking primarily relies on external sensors, which increases system complexity. METHODS: Here, we propose a learning-driven framework, in which an image-guided laparoscopic localization with 3D reconstructions of anatomical structures is obtained. To reconstruct the structure of the whole surgical environment, we first fine-tune a learning-based stereoscopic depth perception method, which is robust to texture-less and variant soft tissues, for depth estimation. Then, we develop a dense reconstruction algorithm to represent the scene by surfels, estimate the laparoscope poses and fuse the depth into a unified reference coordinate for tissue reconstruction. To estimate poses of new laparoscope views, we achieve a coarse-to-fine localization method, which incorporates our reconstructed model. RESULTS: We evaluate the reconstruction method and the localization module on three datasets, namely, the stereo correspondence and reconstruction of endoscopic data (SCARED), the ex-vivo data collected with Universal Robot (UR) and Karl Storz Laparoscope, and the in-vivo DaVinci robotic surgery dataset, where the reconstructed structures have rich details of surface texture with an error under 1.71 mm and the localization module can accurately track the laparoscope with images as input. CONCLUSIONS: Experimental results demonstrate the superior performance of the proposed method in anatomy reconstruction and laparoscopic localization. SIGNIFICANCE: The proposed framework can be potentially extended to the current surgical navigation system.

Asunto(s)

Laparoscopía , Cirugía Asistida por Computador , Laparoscopios , Imagenología Tridimensional/métodos , Procedimientos Quirúrgicos Mínimamente Invasivos/métodos , Laparoscopía/métodos , Algoritmos , Cirugía Asistida por Computador/métodos

RESUMEN

Laser beam steering has been widely studied for the automation of surgery. Currently, flexible instruments for laser surgery are operated entirely by surgeons, which keeps the automation of endoluminal surgery at the initial level. This paper introduces the design of a new workflow that enables the task autonomy of laser-assisted surgery in constrained environments such as the gastrointestinal (GI) tract with a flexible continuum robotic system. Unlike current, laser steering systems driven by piezoelectric require the use of high voltage and are risky. This paper describes a tendon-driven 2 mm diameter flexible manipulator integrated with an endoscope to steer the laser beam. By separating its motion from the total endoscopic system, the designed flexible manipulator can automatically manipulate the laser beam. After the surgical site is searched by the surgeon with a master/slave control, a population-based model-free control method is applied for the flexible manipulator to achieve accurate laser beam steering while overcoming the noise from the visual feedback and disturbances from environment during operation. Simulations and experiments are performed with the system and control methods to demonstrate the proposed framework in a simulated constrained environment.