Neural Adaptive Tomography

Neural Adaptive Tomography (NeAT) is a rapidly developing field leveraging deep learning to improve the speed and accuracy of tomographic image reconstruction across various applications, including medical imaging and remote sensing. Current research focuses on refining neural network architectures, such as convolutional and iterative networks, to address challenges like motion artifacts, noise resilience, and handling complex topologies in reconstructed 3D volumes. These advancements promise significant improvements in image quality and efficiency for existing tomographic techniques, leading to faster scans, reduced radiation exposure, and enhanced diagnostic capabilities.