Problem: One of the biggest challenges in hospitals today is improving efficiency, (patient) safety and quality of care while cutting on costs. A current reoccurring challenge in the operation department is the coordination of the components involved in making a surgery successful. One of those components is the set of surgical instruments. They undergo a cyclic process using reprocessing methods during which various challenges arise. A few of these challenges are the complex and time-consuming instrument counts before, during and after surgery.
Research question: Various technological aids have been proposed to automate the instrument counts. Previous technologies all showed their own flaws when they were tested in the operation room (OR). A new research field for the purpose of instrument counting is the use of computer vision. Computer vision shows great promise as it is already widely used to detect and recognize objects in digital images. However, before developing an algorithm to be used specifically for surgical instrument counting in and around the OR, the various activities, working methods and environmental factors are investigated first. This is done using the following research question: "What is the feasibility of using a computer vision algorithm to automatically detect and count surgical instruments and what are potential factors that influence the performance and the implementation in the OR?".

Methods: The research question is answered using a converting thesis structure. Firstly,
the most general steps of the instrument cycle are outlined and a description is given of a SIFT computer vision algorithm. SIFT is the proposed algorithm type for the investigated application. Secondly, the more specific steps of the instrument cycle at the Reinier de Graaf Gasthuis (RdGG) are described. The result of this description are different application options and different design scenarios. Thirdly, one application type and design scenario is selected: instrument counts in the OR. A blueprint is given for testing a SIFT algorithm in the OR. This blueprint could result in numerical results, valuable observations in the OR and staff survey results.
Results: A total of 35 surgeries were attended. Only results from observations and the survey are shown as the algorithm itself was not tested yet. The observations showed factors that could negatively influence the algorithm’s performance. The survey results gave valuable insights into personal opinions on the value, use and implementation of the algorithm. 
Conclusion: The feasibility of a current SIFT algorithm in a current ORs is low as it will not be able to automatically detect and count all instruments. There are a lot of factors that need to be taken into account to improve performance and possible implementation. They are formulated in 5 design focus points: 1) a line of sight between camera and the instrument(s), 2) dealing with instruments being taken away from and added to the table, 3) controlling the light conditions around the instrument table, 4) recognizing the specific type of some instruments and 5) showing clear feedback.