The field of medical imaging is rapidly advancing with the development of new reconstruction and synthesis techniques. Recent research has focused on improving the accuracy and efficiency of image reconstruction, particularly in the context of noise reduction and motion correction. For example, new methods have been proposed for calculating voxel-wise variance in MRI reconstructions, allowing for more accurate uncertainty quantification. Additionally, novel approaches have been developed for motion-compensated image reconstruction, enabling the reduction of motion artifacts in images. Furthermore, advances in image synthesis have enabled the generation of high-quality synthetic images, which can be used to supplement existing datasets and improve the accuracy of downstream tasks. Noteworthy papers in this area include Efficient Noise Calculation in Deep Learning-based MRI Reconstructions, which proposes a memory-efficient technique for calculating voxel-wise variance, and ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis, which introduces a novel framework for pathology-aware image synthesis. Overall, these advances have the potential to significantly improve the quality and accuracy of medical images, leading to better diagnosis and treatment of diseases.