Based on a stochastic mutual information type matching and RPROP as stochastic optimizer, an interactive image-based registration of a CT volume onto two 2D images provided by a megavoltage system is presented. The matching process is based on semi-automatic presegmentation, an approximate 2D-2D matching with precomputed virtual projections (DRRs) followed by an accurate 3D-2D matching step. Our sample-based approach requires only a fraction of computed DRRs for 3D-2D. A simultaneous computation of the DRR rays and their perturbations in 6 dimensions speeds up the rendering process by a factor of 6.8. The complete registration process takes 5.6 ± 2.3 seconds on a 3 GHz Pentium IV PC, being the fastest non-parallel approach for this sort of application the authors are aware of. © 2006 The authors. All rights reserved.
Fast rigid registration in radiation therapy / Muller, U.; Hesser, J.; Walter, C.; Dobler, B.; Lohr, F.; Wenz, F.. - 119:(2006), pp. 404-406. (Intervento presentato al convegno Medicine Meets Virtual Reality 14 - Accelerating Change in Healthcare: Next Medical Toolkit, MMVR 2006 tenutosi a Long Beach, CA, usa nel JAN 24-27, 2006).
Fast rigid registration in radiation therapy
Lohr F.;
2006
Abstract
Based on a stochastic mutual information type matching and RPROP as stochastic optimizer, an interactive image-based registration of a CT volume onto two 2D images provided by a megavoltage system is presented. The matching process is based on semi-automatic presegmentation, an approximate 2D-2D matching with precomputed virtual projections (DRRs) followed by an accurate 3D-2D matching step. Our sample-based approach requires only a fraction of computed DRRs for 3D-2D. A simultaneous computation of the DRR rays and their perturbations in 6 dimensions speeds up the rendering process by a factor of 6.8. The complete registration process takes 5.6 ± 2.3 seconds on a 3 GHz Pentium IV PC, being the fastest non-parallel approach for this sort of application the authors are aware of. © 2006 The authors. All rights reserved.
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
