Automatic Detection of Misalignment in Rigid 3D-2D Registration

Fusion of pre-interventional three-dimensional (3D) image to live two-dimensional (2D) image can facilitate minimally invasive image-guided interventions. For this purpose a number of 3D-2D registration methods related to different clinical contexts were proposed, however, their translation into clinical theater is still limited by lack of reliable and automatic detection of 3D-2D misalignment. In this paper, we presented a novel approach for verifying 3D-2D misalignment based on learned a priori knowledge using arbitrary similarity measure (SM) and single synthetic image (DRR). First, positions of local optima of SM using DRR image were found and characterized. On live 2D image, the local optima of SM were comparatively examined at the expected, previously learned positions. The approach was tested on publicly available image database of lumbar spine using state-of-the-art back-projection gradient-based SM. The results indicate that proposed approach successfully discriminated the "correct" from "poor" and "wrong" 3D-2D alignments in 100 % of cases.