Needle tracking through higher-order MRF optimization

We propose a Markov Random Field formulation for the tracking of needles in fluoroscopic images. A novel motion model makes it possible to capture the primarily rigid motion as well as deformations of the needle in a single second-order MRF graph. Needles are represented by B-splines and each control point is associated with a random variable in a MAP-MRF formulation. In addition to the control points we introduce a single additional random variable representing the rigid transformation needles undergo during interventions. The incorporation of rigid transformations allows to recover transformations even in the presence of large displacements which is not possible with existing MRF models for medical tool tracking.