Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization
ACM Transactions on Mathematical Software (TOMS)
Validation of registration accuracy
Handbook of medical imaging
Multi-modal Image Registration by Minimising Kullback-Leibler Distance
MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part II
Toward a Common Validation Methodology for Segmentation and Registration Algorithms
MICCAI '00 Proceedings of the Third International Conference on Medical Image Computing and Computer-Assisted Intervention
No free lunch theorems for optimization
IEEE Transactions on Evolutionary Computation
Computer Methods and Programs in Biomedicine
Computers in Biology and Medicine
A unified image registration framework for ITK
WBIR'12 Proceedings of the 5th international conference on Biomedical Image Registration
Hi-index | 0.00 |
We present an image registration framework which offers effective assistance for solving current registration problems. This work was motivated by the huge amount of registration problems in clinical applications and the problem of finding adequate solutions and properly comparing them. We have therefore designed a framework that supports the establishment, evaluation and comparison of registration approaches. Flexible registration and evaluation engine (f.r.e.e.) achieves a broad basis of algorithms by utilizing the insight segmentation and registration toolkit (ITK). This basis can be extended by virtually any new approach or algorithm, which then becomes seamlessly integrated into the method set of the f.r.e.e. framework. The framework offers suitable tools for an easy integration, optimization and proper evaluation of registration approaches, as well as an efficient utilization of the results in clinical routine. The framework is currently being evaluated at the Heidelberg University Hospital, Germany. The first results were gathered with an application implemented for the Neurosurgical Department of the hospital. In these tests the framework concept, along with its specific tools, was very promising for establishing clinical applications (e.g. preoperative neurosurgical planning; registration of cardiac images) and therefore motivated further development. The ability to automatically optimize the parameterization of registration methods regarding a given test set also proved useful, allowing more concentration on scientific problems themselves and not on the laborious task of parameter tweaking. Due to implemented abstraction layers, f.r.e.e. also allows a high degree of transparency and thus good comparability of registration approaches and results.