Purpose: Single Incision Laparoscopic Surgery (SILS) decreases post-operative infections, but introduces limitations in the surgeon's manoeuverability and in the surgical field of view. This work aims at enhancing intraoperative surgical visualization by exploiting the 3D information about the surgical site. An interactive guidance system is proposed wherein the pose of pre-operative tissue models is updated online. A critical process involves the intraoperative acquisition of tissue surfaces. It can be achieved using stereoscopic imaging and 3D reconstruction techniques. This work contributes to this process by proposing new methods for improved dense 3D reconstruction of soft tissues, which allows a more accurate deformation identification and facilitates the registration process.Methods: Two methods for soft tissue 3D reconstruction are proposed: Method 1 follows the traditional approach of the block matching algorithm. Method 2 performs a non-parametric Modified Census Transform to be more robust to illumination variation. The Simple Linear Iterative Clustering (SLIC) super pixel al- gorithm is exploited for disparity refinement by filling holes in the disparity images.Results: The methods were validated using two video datasets from the Hamlyn Centre, achieving an accuracy of 2.95 mm and 1.66 mm respectively. A comparison with ground truth data demonstrated the disparity refinement procedure: (i) increases the number of reconstructed points by up to 43%; (ii) does not a↵ect the accuracy of the 3D reconstructions significantly.Conclusion: Both methods give results that compare favourably with the state-of-the-art methods. The computational time constraints their applicability in realtime, but can be greatly improved by using a GPU implementation.

The EndoAbS dataset contributes to an increase the number and variety of openly available datasets of surgical stereo images, including a highly accurate RF and different surgical conditions.

In abdominal surgery, intraoperative bleeding is one of the major complications that affect the outcome of minimally invasive surgical procedures. One of the causes is attributed to accidental damages to arteries or veins, and one of the possible risk factors falls on the surgeon's skills. This paper presents the development and application of an Enhanced Vision System for Robotic Surgery (EnViSoRS), based on a user-defined Safety Volume (SV) tracking to minimize the risk of intraoperative bleeding. It aims at enhancing the surgeon's capabilities by providing Augmented Reality (AR) assistance toward the protection of vessels from injury during the execution of surgical procedures with a robot. The core of the framework consists in (i) a hybrid tracking algorithm (LT-SAT tracker) that robustly follows a user-defined Safety Area (SA) in long term; (ii) a dense soft tissue 3D reconstruction algorithm, necessary for the computation of the SV; (iii) AR features for visualization of the SV to be protected and of a graphical gage indicating the current distance between the instruments and the reconstructed surface. EnViSoRS was integrated with a commercial robotic surgical system (the dVRK system) for testing and validation. The experiments aimed at demonstrating the accuracy, robustness, performance, and usability of EnViSoRS during the execution of a simulated surgical task on a liver phantom. Results show an overall accuracy in accordance with surgical requirements (<5 mm), and high robustness in the computation of the SV in terms of precision and recall of its identification. The optimization strategy implemented to speed up the computational time is also described and evaluated, providing AR features update rate up to 4 fps, without impacting the real-time visualization of the stereo endoscopic video. Finally, qualitative results regarding the system usability indicate that the proposed system integrates well with the commercial surgical robot and has indeed potential to offer useful assistance during real surgeries.