Cardiac phase-correlated image reconstruction and advanced image processing in pulmonary CT imaging

Image quality in pulmonary CT imaging is commonly degraded by cardiac motion artifacts. Phase-correlated image reconstruction algorithms known from cardiac imaging can reduce motion artifacts but increase image noise and conventionally require a concurrently acquired ECG signal for synchronization. Techniques are presented to overcome these limitations. Based on standard and phase-correlated images that are reconstructed using a raw data-derived synchronization signal, image-merging and temporal-filtering techniques are proposed that combine the input images automatically or interactively. The performance of the approaches is evaluated in patient and phantom datasets. In the automatic approach, areas of strong motion and static areas were well detected, providing an optimal combination of standard and phase-correlated images with no visible border between the merged regions. Image noise in the non-moving regions was reduced to the noise level of the standard reconstruction. The application of the interactive filtering allowed for an optimal adaptation of image noise and motion artifacts. Noise content after interactive filtering decreased with increasing temporal filter width used. We conclude that a combination of our motion-free merging approach and a dedicated interactive filtering procedure can highly improve pulmonary imaging with respect to motion artifacts and image noise.