In this paper, we propose a novel approach to landmark-based shape representation that is based on transportation theory, where landmarks are considered as sources and destinations, all possible landmark connections as roads, and established landmark connections as goods transported via these roads. Landmark connections, which are selectively established, are identified through their statistical properties describing the shape of the object of interest, and indicate the least costly roads for transporting goods from sources to destinations. From such a perspective, we introduce three novel shape representations that are combined with an existing landmark detection algorithm based on game theory. To reduce computational complexity, which results from the extension from 2-D to 3-D segmentation, landmark detection is augmented by a concept known in game theory as strategy dominance. The novel shape representations, game-theoretic landmark detection and strategy dominance are combined into a segmentation framework that was first evaluated on 3-D computed tomography images of lumbar vertebrae and femoral heads and later on intracranial vasculature. The best shape representation yielded a Dice coefficient between 93.6% and 96.2%, indicating a very good segmenation.
COBISS.SI-ID: 10360660
Visualization and analysis of intra-operative images in image-guided radiotherapy and surgery are mainly limited to 2D X-ray imaging, which could be beneficially fused with information-rich pre-operative 3D image information by means of 3D-2D image registration. To keep the radiation dose delivered by the X-ray system low, the intra-operative imaging is usually limited to a single projection view. Registration of 3D to a single 2D image is a very challenging registration task for most of current state-of-the-art 3D-2D image registration methods. We propose a novel 3D-2D rigid registration method based on evaluation of similarity between corresponding 3D and 2D gradient covariances, which are mapped into the same space using backprojection. Normalized scalar product of covariances is computed as similarity measure. Performance of the proposed and state-of-the-art 3D-2D image registration methods was evaluated on two publicly available image datasets, one of cerebral angiograms and the other of a spine cadaver, using standardized evaluation methodology. Results showed that the proposed method outperformed the current state-of-the-art methods and achieved registration accuracy of 0.5 mm, capture range of 9 mm and success rate )80%. Considering also that GPU-enabled execution times ranged from 0.5-2.0 seconds, the proposed method has the potential to enhance with 3D information the visualization and analysis of intra-operative 2D images.
COBISS.SI-ID: 10703444
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.
COBISS.SI-ID: 10537812