Scintillator decorrelation for self-supervised x-ray radiograph denoising

Abstract X-ray radiographs from industrial, medical, and laboratory x-ray equipment can degrade severely due to fast and/or low-dose acquisition, x-ray scatter, and electronic noise from the detector instrument. As a consequence, noise and artifacts propagate into computed tomography (CT) images. Recently, a new class of self-supervised deep learning methods, with Noise2Self and Noise2Void, demonstrated state-of-the-art denoising results on data sets of pixelwise statistically-independent noisy images. These methods, called blind-spot networks (BSNs), are promising for applications where clean training examples or pairs of noisy examples are unavailable. For x-ray imaging, however, the detection principle of x-ray scintillators leads to a spatially-correlated mix of Poisson and Gaussian noise, rendering BSNs ineffective. In this article, we propose and validate a denoising workflow that reverts the correlations by a direct deconvolution with an estimate of the scintillator point-response function . We show that it can restore the denoising performance of Noise2Self, and demonstrate it for dynamic sparse-view CT reconstruction of single-bubble gas-solids fluidized beds using a data set of unpaired noisy radiographs from cesium-iodine scintillator flat-panel detectors.