Computed Tomography Reconstruction

Computed tomography (CT) reconstruction aims to create high-resolution 3D images from a series of X-ray projections, balancing image quality with radiation exposure. Current research heavily emphasizes developing novel algorithms, often leveraging deep learning architectures like diffusion models, generative adversarial networks (GANs), and convolutional neural networks (CNNs), to improve reconstruction from sparse-view or low-dose data, and even from fewer X-ray projections (e.g., biplanar or monoplanar). These advancements are crucial for reducing patient radiation exposure in medical settings, enabling faster industrial processes, and facilitating applications where full CT scans are impractical, such as image-guided surgery. Improved reconstruction techniques also enhance the accuracy and efficiency of various medical and industrial applications.