Biomechanics-machine learning system for surgical gesture analysis and development of technologies for minimal access surgery.

Background: The uptake of minimal access surgery (MAS) has by virtue of its clinical benefits become widespread across the surgical specialties. However, despite its advantages in reducing traumatic insult to the patient, it imposes significant ergonomic restriction on the operating surgeons who require training for the safe execution. Recent progress in manipulator technologies (robotic or mechanical) have certainly reduced the level of difficulty, however it requires information for a complete gesture analysis of surgical performance.

Proficiency assessment of gesture analysis in laparoscopy by means of the surgeon's musculo-skeleton model.

Objective: This article presents the implementation of surgeon's musculo-skeletal model for gesture analysis in laparoscopy, thereby providing a complete account of the objective metrics needed to evaluate surgical performance and to improve the design of new surgical instruments including robotic instrumentation for surgical procedures.

Background: Previous published work has been based exclusively on the kinematics involved whereas, this study is focused on the dynamics and muscle contraction analysis to assess loads on bones and muscle fatigue during simulation of surgical interventions.

Methods: Nine medical students and 2 fully trained surgeons participated in the experimental sessions using a virtual laparoscopic simulator.

A 3-D mixed-reality system for stereoscopic visualization of medical dataset.

We developed a simple, light, and cheap 3-D visualization device based on mixed reality that can be used by physicians to see preoperative radiological exams in a natural way. The system allows the user to see stereoscopic "augmented images," which are created by mixing 3-D virtual models of anatomies obtained by processing preoperative volumetric radiological images (computed tomography or MRI) with real patient live images, grabbed by means of cameras. The interface of the system consists of a head-mounted display equipped with two high-definition cameras.

Hand-held robotic instrument for dextrous laparoscopic interventions.

Background: Surgical instruments used in many types of minimally invasive procedures are rigid or only limitedly flexible. Some common tasks like suturing, require precise and dextrous movements that are difficult to perform by means of instruments with limited degrees of freedom (DOF).

Methods: A hand-held lightweight and ergonomic robotic instrument with a 3-DOF roll-pitch-roll end-effector has been developed, which can be controlled by the surgeon with one hand like a conventional instrument.

EndoCAS navigator platform: a common platform for computer and robotic assistance in minimally invasive surgery.

Background: Computer-assisted surgery (CAS) systems are currently used in only a few surgical specialties: ear, nose and throat (ENT), neurosurgery and orthopaedics. Almost all of these systems have been developed as dedicated platforms and work on rigid anatomical structures. The development of augmented reality systems for intra-abdominal organs remains problematic because of the anatomical complexity of the human peritoneal cavity and especially because of the deformability of its organs.

Defining brain-machine interface applications by matching interface performance with device requirements.

Interaction with machines is mediated by human-machine interfaces (HMIs). Brain-machine interfaces (BMIs) are a particular class of HMIs and have so far been studied as a communication means for people who have little or no voluntary control of muscle activity. In this context, low-performing interfaces can be considered as prosthetic applications.

Tracking endoscopic instruments without a localizer: a shape-analysis-based approach.

We present an approach to localizing endoscopic instruments with respect to the camera position, based purely on processing of the endoscope image. No localizers are needed; the only requirement is a colored strip at the distal part of the instrument shaft to facilitate image segmentation. The method exploits perspective image analysis applied to the cylindrical shape of the instrument shaft, allowing measurement of the instrument position and orientation with five degrees of freedom.

Comparison of control modes of a hand-held robot for laparoscopic surgery.

Teleoperated robots for minimally invasive surgery make surgeons loose direct contact with the patient. We are developing a handheld, dexterous surgical robot that can be controlled with one hand only, while standing at the operating table. The instrument is composed of a master part (the handle) and a slave part (the tip).

Modelling and evaluation of surgical performance using hidden Markov models.

Minimally invasive surgery has become very widespread in the last ten years. Since surgeons experience difficulties in learning and mastering minimally invasive techniques, the development of training methods is of great importance. While the introduction of virtual reality-based simulators has introduced a new paradigm in surgical training, skill evaluation methods are far from being objective.

Tracking endoscopic instruments without localizer: image analysis-based approach.

In this paper we present an approach to localize endoscopic instruments with respect to the camera position, purely based on video image processing. No localizers are required. The only requirement is a coloured strip at the distal part of the instrument shaft, to facilitate image segmentation.

A biomechanical analysis of surgeon's gesture in a laparoscopic virtual scenario.

Minimally invasive surgery (MIS) has become very common in recent years thanks to many advantages that patients can get. However, due to the difficulties surgeons encounter to learn and manage this technique, several training methods and metrics have been proposed in order to, respectively, improve surgeon's abilities and assess his/her surgical skills. In this context, this paper presents a biomechanical analysis method of the surgeon's movements, during exercise involving instrument tip positioning and depth perception in a laparoscopic virtual environment.