Radon Transform

The Radon transform is a mathematical tool that projects a function onto lines, effectively transforming a multi-dimensional signal into a collection of line integrals. Current research focuses on leveraging the Radon transform in diverse applications, including image registration, probability density estimation, and computed tomography (CT) reconstruction, often employing techniques like deep neural networks and novel algorithms such as Hierarchical Hybrid Sliced Wasserstein distance to improve efficiency and robustness. These advancements are improving the accuracy and speed of various image processing and analysis tasks, particularly in medical imaging where reducing radiation dosage and mitigating artifacts are crucial. The transform's ability to handle high-dimensional data and its adaptability to different problem formulations make it a valuable tool across numerous scientific disciplines.