Numerical recipes in C (2nd ed.): the art of scientific computing
Numerical recipes in C (2nd ed.): the art of scientific computing
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Correlation Ratio as a New Similarity Measure for Multimodal Image Registration
MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
MICCAI '99 Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention
Hi-index | 0.00 |
Conformal radiotherapy treatments need accurate patient positioning in order to spare normal tissues. Patient pose can be evaluated by registering portal images (PI) with Digitally Reconstructed Radiographs (DRR). Several methods involve segmentation which is known to be a difficult task for noisy PI. In this paper, we study another approach by using a fully 3D intensity-based registration method, without segmentation. Our approach uses the correlation ratio as similarity measure and replace DRR generation with a treatment on pre-computed DRR. A specific geometrical transformation is applied to approximate a given projection by the composition of out-of-plane rotations and in-plane transformation. Some preliminary experiments on both simulated and real portal images, lead to good results (RMS error lower than 2 mm).