Real-time 2D/3D Registration via CNN Regression
This addresses the need for faster registration in medical imaging, though it is incremental as it builds on existing CNN and registration techniques.
The paper tackles the problem of real-time 2D/3D registration by proposing a CNN regression approach that directly estimates transformation parameters, achieving computational efficiency with negligible accuracy degradation compared to intensity-based methods.
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.