Noise2Filter: fast, self-supervised learning and real-time reconstruction for 3D Computed Tomography
This addresses the need for efficient, real-time reconstruction in synchrotron imaging, though it is incremental as it builds on existing quasi-3D and learned filter approaches.
The paper tackles the problem of noise sensitivity in quasi-3D reconstruction for real-time 3D computed tomography by proposing Noise2Filter, a self-supervised learned filter method that trains in under a minute and enables real-time evaluation with improved accuracy over standard filters.
At X-ray beamlines of synchrotron light sources, the achievable time-resolution for 3D tomographic imaging of the interior of an object has been reduced to a fraction of a second, enabling rapidly changing structures to be examined. The associated data acquisition rates require sizable computational resources for reconstruction. Therefore, full 3D reconstruction of the object is usually performed after the scan has completed. Quasi-3D reconstruction -- where several interactive 2D slices are computed instead of a 3D volume -- has been shown to be significantly more efficient, and can enable the real-time reconstruction and visualization of the interior. However, quasi-3D reconstruction relies on filtered backprojection type algorithms, which are typically sensitive to measurement noise. To overcome this issue, we propose Noise2Filter, a learned filter method that can be trained using only the measured data, and does not require any additional training data. This method combines quasi-3D reconstruction, learned filters, and self-supervised learning to derive a tomographic reconstruction method that can be trained in under a minute and evaluated in real-time. We show limited loss of accuracy compared to training with additional training data, and improved accuracy compared to standard filter-based methods.