2016 · 99 citations · 12 references
ComputingComputer ScienceRadiologyComputer VisionDiagnostic ImagingDiagnostic Radiology3D Imaging3D ReconstructionComputed TomographyImage ReconstructionImage RegistrationThree-dimensional Reconstruction2D-to-3d Registration3D Image RegistrationComputational EfficiencyConvolutional Neural NetworksDeep Learning-based RegistrationReal-time RegistrationRegistration AccuracyTransformation Parameters
In this paper, we present a Convolutional Neural Network (CNN) regression approach for real-time 2-D/3-D registration. Different from optimization-based methods, which iteratively optimize the transformation parameters over a scalar-valued metric function representing the quality of the registration, the proposed method exploits the information embedded in the appearances of the Digitally Reconstructed Radiograph and X-ray images, and employs CNN regressors to directly estimate the transformation parameters. The CNN regressors are trained for local zones and applied in a hierarchical manner to break down the complex regression task into simpler sub-tasks that can be learned separately. Our experiment results demonstrate the advantage of the proposed method in computational efficiency with negligible degradation of registration accuracy compared to intensity-based methods.
12
Yangqing Jia, Evan Shelhamer, Jeff Donahue et al. · 2014 · 11.2K citations
Standardized evaluation methodology for 2-D-3-D registration
Everine B. van de Kraats, Graeme Penney, Dejan Tomaževič et al. · IEEE Transactions on Medical Imaging · 2005 · 214 citations
Monitoring tumor motion by real time 2D/3D registration during radiotherapy
Christelle Gendrin, Hugo Furtado, Christoph Weber et al. · Radiotherapy and Oncology · 2011 · 86 citations · Full text