Materials and methods: Two registration methods based on optical flow estimation have been programmed to run on a graphics programming unit (GPU). One of these methods by Horn & Schunck is tested on a 4DCT thorax data set with 10 phases and 41 landmarks identified per phase. The other method by Cornelius & Kanade is tested on a series of six 3D cone beam CT (CBCT) data sets and a conventional planning CT data set from a head and neck cancer patient. In each of these data sets 6 landmark points have been identified on the cervical vertebrae and the base of skull. Both CBCT to CBCT and CBCT to CT registration is performed.Results: For the 4DCT registration average landmark error was reduced by deformable registration from 3.5 ± 2.0 mm to 1.1 ± 0.6 mm. For CBCT to CBCT registration the average bone landmark error was 1.8 ± 1.0 mm after rigid registration and 1.6 ± 0.8 mm after deformable registration. For CBCT to CT registration errors were 2.2 ± 0.6 mm and 1.8 ± 0.6 mm for rigid and deformable registration respectively. Using GPU hardware the Horn & Schunck method was accelerated by a factor of 48. The 4DCT registration can be performed in 37 seconds. The head and neck cancer patient registration takes 64 seconds.Discussion: Compared to image slice thickness, which limits accuracy of landmark point determination, we consider the landmark point accuracy of the registration acceptable. The points identified in the CBCT images do not give a full impression of the result of doing deformable registration as opposed to rigid registration. A larger validation study is being planned in which soft tissue landmarks will facilitate tracking the deformableregistration. The acceleration obtained using GPU hardware means that registration can be done online for CBCT.< Leer menos