Using SciKit-Surgery for Augmented Reality in Surgery

Abstract

SciKit-Surgery provides open source libraries to support research and translation of applications for augmented reality in surgery [1]. This paper discusses recent de- velopments in SciKit-Surgery and case studies using SciKit-SurgeryBARD to support research into visuali- sation and user interface design for augmented reality in surgery [2], [3]. The availability of high quality software tools for re- search and translation is a key enabler for scientific progress. Research into surgical robotics, image guided surgery, and augmented reality for surgery brings to- gether many disciplines and depends on a strong en- gineering base to provide the tools that researchers need (e.g., hardware interfaces, data management, data processing, visualisation, and user interfaces). SciKit- Surgery was conceived as a more accessible replacement for existing toolkits written predominantly in C++. Ex- perience has taught us that whilst implementations in C++ could be robust and offer optimised performance, the need to learn the language and the difficulties of maintaining cross platform compilation presented a higher a barrier of entry for most researchers. Whilst research software can be initially developed using short term research grants, the longer term sustainability of the software depends on other researchers being able to contribute to the software, both for maintenance and to introduce new features. For that to happen the software needs to be compact, written in a language that be easily interpreted by humans, and well documented. We conceived SciKit-Surgery to be a set of individual Python modules that could be used on their own by researchers to explore a specific topic or assembled into high quality applications that could be rapidly deployed to clinic to enable translation from bench to bedside.