Abstract. Vision-based tracking of laparoscopic tools offers new possibilities for improving surgical training and for developing new augmented reality surgical applications. We present an original method to determine not only the tip position, but also the orientation of a laparoscopic tool respect to the camera coordinate frame. A simple mathematical formulation shows how segmented tool edges and camera field of view define the tool 3D orientation. Then, 3D position of the tool tip is determined by image 2D coordinates of any known point of the tool and by tool's diameter. Accuracy is evaluated in real image sequences with known ground truth. Results show a positioning error of 9,28 mmRMS, what is explained by inaccuracies in the estimation of tool edges. The main advantage of proposed method is its robustness to occlusions of the tool tip.

Automatic analysis of Minimally Invasive Surgical video has the potential to drive new solutions for alleviating needs of safe and reproducible training programs, objective and transparent evaluation systems and navigation tools to assist surgeons and improve patient safety. Surgical video is an always available source of information, which can be used without any additional intrusive hardware in the operating room. This paper is focused on surgical video analysis methods and techniques. It describes authors' contributions in two key aspects, the 3D reconstruction of the surgical field and the segmentation and tracking of tools and organs based on laparoscopic video images. Results are given to illustrate the potential of this field of research, like the calculi of the 3D position and orientation of a tool from its 2D image, or the translation of a preoperative resection plan into a hepatectomy surgical procedure using the shading information of the image. Research efforts are required to further develop these technologies in order to harness all the valuable information available in any video-based surgery.tool tracking, organ reconstruction

No abstract

No abstract

Abstract.A trend in abdominal surgery is the transition from minimally invasive surgery to surgeries where augmented reality is used. Endoscopic video images are proposed to be employed for extracting useful information to help surgeons performing the operating techniques. This work introduces an illumination model into the design of automatic segmentation algorithms and 3D reconstruction methods. Results obtained from the implementation of our methods to real images are supposed to be an initial step useful for designing new methodologies that will help surgeons operating MIS techniques.