Motion-guided resolution enhancement for Lung 4D-CT

Lung 4D-CT provides important anatomical structure and motion information, which can be crucial in radiation therapy for lung cancer. However, radiation dose concerns limit the number of axial slices in 4D-CT, resulting in low superior-inferior resolution. We propose an approach to estimate the intermediate slices for resolution enhancement of 4D-CT. We explore the lung-motion-induced locally complimentary sampling information across respiratory phases, by using the deformation fields between 3D phase-volumes. For better robustness to noise and registration errors, we estimate the unknown intermediate slices in a patch-wise manner. To this end, we compute candidate patches from the available slices in different phases, based on the deformation field estimates. We then linearly combine the candidate patches, using weights computed by solving an h minimization problem. Unlike state-of-the-art methods, our deformation-driven patch-based approach requires a small number of inter-phase candidate patches, and yet outperforms these methods. This highlights the usefulness of considering deformation information in resolution enhancement of lung 4D-CT.