A remark on computing distance functions
Journal of Computational Physics
A Scale-Space Approach to Nonlocal Optical Flow Calculations
SCALE-SPACE '99 Proceedings of the Second International Conference on Scale-Space Theories in Computer Vision
A Variational Framework for Joint Segmentation and Registration
MMBIA '01 Proceedings of the IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA'01)
Multiscale Joint Segmentation and Registration of Image Morphology
IEEE Transactions on Pattern Analysis and Machine Intelligence
A 2D-spline patient specific model for use in radiation therapy
ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Time-of-Flight sensor calibration for accurate range sensing
Computer Vision and Image Understanding
Range map superresolution-inpainting, and reconstruction from sparse data
Computer Vision and Image Understanding
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II
Hi-index | 0.00 |
The management of intra-fractional respiratory motion is becoming increasingly important in radiation therapy. Based on in advance acquired accurate 3D CT data and intra-fractionally recorded noisy time-of-flight (ToF) range data an improved treatment can be achieved. In this paper, a variational approach for the joint registration of the thorax surface extracted from a CT and a ToF image and the denoising of the ToF image is proposed. This enables a robust intra-fractional full torso surface acquisition and deformation tracking to cope with variations in patient pose and respiratory motion. Thereby, the aim is to improve radiotherapy for patients with thoracic, abdominal and pelvic tumors. The approach combines a Huber norm type regularization of the ToF data and a geometrically consistent treatment of the shape mismatch. The algorithm is tested and validated on synthetic and real ToF/CT data and then evaluated on real ToF data and 4D CT phantom experiments.