4D Cardiac Volume Reconstruction from Free-Breathing 2D Real-Time Image Acquisitions using Iterative Motion Correction

For diagnosis, treatment and study of various cardiac diseases directly affecting the functionality and morphology of the heart, physicians rely more and more on MR imaging techniques. MRI has good tissue contrast and can achieve high spatial and temporal resolutions. However it requires a relatively long time to obtain enough data to reconstruct useful images. Additionally, when imaging the heart, the occurring motions - breathing and heart beat - have to be taken into account. While the cardiac motion still has to be correctly seen to asses functionality, the respiratory motion has to be removed to avoid serious motion artefacts. We present initial results for a reconstruction pipeline that takes multiple stacks of 2D slices, calculates the occurring deformations for both cardiac and respiratory motions and reconstructs a coherent 4D volume of the beating heart. The 2D slices are acquired during free-breathing over the whole respiratory cycle, using a fast real-time technique. For motion estimation two different transformation models were used. A cyclic 4D B-spline free-form deformation model for the cardiac motion and a 1D B-spline affine model for the respiratory motion. Both transformations and the common reference frame needed for the registration are optimized in an interleaved, iterative scheme.