Based on the acquisition trajectory, PROPELLER MRI repeatedly sampled the center k-space in every blade, which was used to provide most of the energy of an image. The purpose of view sharing PROPELLER is to improve the spatio-temporal resolution of dynamic imaging by reducing the acquisition time of single frame to that of single blade. With the center k-space provided by only one blade, which is called the target blade, the high spatial-frequency components were appropriately contributed by a set of neighboring blades with different rotation angles, leading to the high spatial resolution after reconstruction. In this study, a flow phantom experiment with the injection of T1-shortening Gd-DTPA solution was performed to exam the feasibility and accuracy of view-sharing PROPELLER. Furthermore, cardiac imaging of healthy volunteer obtained by the proposed technique was also done with ECG gating to test the image quality without any injection of contrast agent. The in-vivo experiment was done with and without breath holding. In addition to slight aliasing artifact due to insufficient FOV, no other artifact was observed.

One of the major obstacles for designing solutions against the imminent climate crisis is the scarcity of high spatio-temporal resolution model projections for variables such as precipitation. This kind of information is crucial for impact studies in fields like hydrology, agronomy, ecology, and risk management. The currently highest spatial resolution datasets on a daily scale for projected conditions fail to represent complex local variability. We used deep-learning-based statistical downscaling methods to obtain daily 1 km resolution gridded data for precipitation in the Eastern Ore Mountains in Saxony, Germany. We built upon the well-established climate4R framework, while adding modifications to its base-code, and introducing skip connections-based deep learning architectures, such as U-Net and U-Net++. We also aimed to address the known general reproducibility issues by creating a containerized environment with multi-GPU (graphic processing unit) and TensorFlow's deterministic operations support. The perfect prognosis approach was applied using the ERA5 reanalysis and the ReKIS (Regional Climate Information System for Saxony, Saxony-Anhalt, and Thuringia) dataset. The results were validated with the robust VALUE framework. The introduced architectures show a clear performance improvement when compared to previous statistical downscaling benchmarks. The best performing architecture had a small increase in total number of parameters, in contrast with the benchmark, and a training time of less than 6 min with one NVIDIA A-100 GPU. Characteristics of the deep learning models configurations that promote their suitability for this specific task were identified, tested, and argued. Full model repeatability was achieved employing the same physical GPU, which is key to build trust in deep learning applications. The EURO-CORDEX dataset is meant to be coupled with the trained models to generate a high-resolution ensemble, which can serve as input to multi-purpose impact models.