Algorithmic solutions for live device-to-vessel match

An overlay of diagnostic angiograms and interventional fluoroscopy during minimally invasive cathlab interventions can support navigation but suffers from artifacts due to mismatch of vessels and interventional devices. Here, weak image features and strict real-time constraints do not allow for standard multi-modality registration techniques. In the presented method, diagnostic angiograms are filtered to extract the imaged vessel structure. A distance-transform of the extracted vessels allows for fast matching with interventionally imaged devices which are extracted with fast local filters only. Competing vessel and object filters are tested on 10 diagnostic angiograms and 25 fluoroscopic frames showing a guidewire. Their performance is tested in comparison to manual segmentations. A newly presented directional stamping-filter based on anisotropic diffusion of local image patches offers the best results for vessel extraction and also improves the guidewire detection. Using these filters, the device-to-vessel match succeeds in 92% of the tested frames. This rate decreases to 75% for an initial mismatch of 16 pixels.

[1]  Thomas Martin Deserno,et al.  Texture-Adaptive Active Contour Models , 2001, ICAPR.

[2]  S. Collins,et al.  Lumen centerline detection in complex coronary angiograms , 1994, IEEE Transactions on Biomedical Engineering.

[3]  Max A. Viergever,et al.  A survey of medical image registration , 1998, Medical Image Anal..

[4]  Kemal Tuncali,et al.  Intraoperative Segmentation and Nonrigid Registration for Image Guided Therapy , 2000, MICCAI.

[5]  M. Schrijver,et al.  Angiographic Image Analysis to Assess the Severity of Coronary Stenoses , 2002 .

[6]  Jürgen Weese,et al.  3D vessel axis extraction using 2D calibrated x-ray projections for coronary modeling , 2003, SPIE Medical Imaging.

[7]  Barbara Martin-Leung,et al.  Software architecture for live enhancement of medical images , 2004, IS&T/SPIE Electronic Imaging.

[8]  S.A.M. Baert,et al.  Three-dimensional guide-wire reconstruction from biplane image sequences for integrated display in 3-D vasculature , 2003, IEEE Transactions on Medical Imaging.

[9]  Johan H. C. Reiber,et al.  A novel measurement technique to assess the effects of coronary brachytherapy in clinical trials , 2002, IEEE Transactions on Medical Imaging.

[10]  Ramin Shahidi,et al.  Validation of medical image processing in image-guided therapy , 2002, IEEE Transactions on Medical Imaging.

[11]  Sabee Molloi,et al.  Vascular tree object segmentation by deskeletonization of valley courses. , 2002, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[12]  Til Aach,et al.  Statistical-model-based identification of complete vessel-tree frames in coronary angiograms , 2004, IS&T/SPIE Electronic Imaging.

[13]  G Valli,et al.  An algorithm for real-time vessel enhancement and detection. , 1997, Computer methods and programs in biomedicine.

[14]  Til Aach,et al.  Spatiotemporal multiscale vessel enhancement for coronary angiograms , 2002, SPIE Medical Imaging.

[15]  Alejandro F. Frangi,et al.  Model-based segmentation of cardiac and vascular images , 2002, Proceedings IEEE International Symposium on Biomedical Imaging.

[16]  Ole Vilhelm Larsen,et al.  Multiresolution retinal vessel tracker based on directional smoothing , 2002, SPIE Medical Imaging.

[17]  Til Aach,et al.  Mutual information based respiration detection , 2003, CARS.

[18]  Olaf Dössel,et al.  Model evaluation and calibration for prospective respiratory motion correction in coronary MR angiography based on 3-D image registration , 2002, IEEE Transactions on Medical Imaging.

[19]  David Atkinson,et al.  A study of the motion and deformation of the heart due to respiration , 2002, IEEE Transactions on Medical Imaging.

[20]  K Doi,et al.  Quantitative evaluation of vessel tracking techniques on coronary angiograms. , 1999, Medical physics.

[21]  Ève Coste-Manière,et al.  Towards endoscopic augmented reality for robotically assisted minimally invasive cardiac surgery , 2001, Proceedings International Workshop on Medical Imaging and Augmented Reality.

[22]  Y Sun,et al.  Automated identification of vessel contours in coronary arteriograms by an adaptive tracking algorithm. , 1989, IEEE transactions on medical imaging.

[23]  Jörg Bredno,et al.  Synthesis of angiographic images using iterative approximation , 2004, SPIE Medical Imaging.