Sciweavers


Publication

Effective 2D-3D Medical Image Registration using Support Vector Machine

14 years 23 days ago
Effective 2D-3D Medical Image Registration using Support Vector Machine
Registration of pre-operative 3D volume dataset and intra-operative 2D images gradually becomes an important technique to assist radiologists in diagnosing complicated diseases. In this paper, we proposed a novel 2D/3D registration framework based on Support Vector Machine (SVM) to compensate the disadvantages of generating large number of Digitally Rendered Radiographs (DRRs) in the stage of intra-operation. Estimated similarity metric distribution could be built up from the relationship between parameters of transform and prior sparse target metric values by means of SVR method. Based on which, global optimal parameters of transform are finally searched out by an optimizer in order to guide 3D volume dataset to match intra-operative 2D image. Experiments reveal that our proposed registration method improved performance compared to conventional registration method and also provided a precise registration result efficiently.
Wenyuan Qi, Lixu Gu
Added 10 Mar 2010
Updated 10 Mar 2010
Type Technical Report
Year 2008
Where SPIE
Authors Wenyuan Qi, Lixu Gu
Comments (0)