Deep Learning Tool Fills in the Blanks in CT Images

Home News

At a hospital, an airport, or even an assembly line, computed tomography (CT) allows us to investigate the otherwise inaccessible interiors of objects without laying a finger on them. Dozens of techniques exist to mathematically reconstruct an object in 3D, but unlike in theoretical research where high-fidelity data may be plentiful, real-world implementations of CT reconstruction encounter several obstacles that can produce image artifacts and degrade reconstruction results. LLNL researchers collaborated with the Computational Imaging Group at Washington University in St. Louis to devise a state-of-the-art ML–based reconstruction tool for when high-quality CT data is in limited supply. The team’s Diffusion Probabilistic Limited-Angle CT Reconstruction (DOLCE) model was exhaustively trained on hundreds of thousands of medical and airport security x-rays to learn how to incrementally refine these images and restore missing data through the deep learning process of diffusion. The team’s paper was accepted to the 2023 International Conference on Computer Vision, one of the most prestigious global computer vision events. Additionally, the LEAP code enables differentiable forward- and back-projection and smoothly integrates with Python to facilitate the DOLCE model’s training process.