Limited-Angle Tomography Reconstruction via Deep End-To-End Learning on Synthetic Data
This addresses the challenge of reconstructing images from incomplete CT scans, which is crucial for medical and scientific applications where full-angle data is unavailable.
The paper tackled the ill-posed problem of limited-angle tomography reconstruction by developing a deep neural network trained on synthetic data, achieving first place in the Helsinki Tomography Challenge 2022 with performance for angles as low as 30° or 40°.
Computed tomography (CT) has become an essential part of modern science and medicine. A CT scanner consists of an X-ray source that is spun around an object of interest. On the opposite end of the X-ray source, a detector captures X-rays that are not absorbed by the object. The reconstruction of an image is a linear inverse problem, which is usually solved by filtered back projection. However, when the number of measurements is small, the reconstruction problem is ill-posed. This is for example the case when the X-ray source is not spun completely around the object, but rather irradiates the object only from a limited angle. To tackle this problem, we present a deep neural network that is trained on a large amount of carefully-crafted synthetic data and can perform limited-angle tomography reconstruction even for only 30° or 40° sinograms. With our approach we won the first place in the Helsinki Tomography Challenge 2022.