Tool usage in open surgery video data
Improving the training process of surgeons as well as the safety and efficiency of surgical procedures is of outmost importance. With recent developments in the fields of deep learning and computer vision there is a growing interest in using these tools to study and analyze surgical procedures by means of video data. While the use of video is an integral part of minimal invasive surgery (MIS), it is not well established in open surgery. Due to different nature of open surgery and MIS they will require unique algorithms. Tool usage is one example. In MIS the video image typically includes 1–2 tool tips. In contrast, during open surgery we see the hands, the tools being used and in many cases the tool try will be in the cameras field of view. Thus, tool detection will require detecting multiple tools in the image and tool usage will require identifying the tools being currently used by the surgeon. In this study, we developed an algorithm for identifying tool usage in open surgery using video data collected on our variable tissue simulator.
Online Disjoint Set Cover Without Prior Knowledge
The disjoint set cover (DSC) problem is a fundamental combinatorial optimization problem concerned
with partitioning the (hyper)edges of a hypergraph into (pairwise disjoint) clusters so that the number of clusters that cover all nodes is maximized. In its online version, the edges arrive one-by-one and should be assigned to clusters in an irrevocable fashion without knowing the future edges. This paper investigates the competitiveness of online DSC algorithms. Specifically, we develop the first (randomized) online DSC algorithm that guarantees a poly-logarithmic (O(log2 n)) competitive ratio without prior knowledge of the hypergraph’s minimum degree. On the negative side, we prove that the competitive ratio of any randomized online DSC algorithm must be at least
Ω( log n/ log log n) (even if the online algorithm does know the minimum degree in advance), thus establishing the first lower bound on the competitive ratio of randomized online DSC algorithms.