Deep Learning-Based Self-Absorption Correction Method for Fan-Beam X-ray Fluorescence CT

During fan-beam X-ray fluorescence computational tomography imaging, the attenuation of incident X-ray and fluorescence x-ray cause poor reconstructed image quality. In this study, a U-net based method is proposed for self-absorption correction in X-ray fluorescence CT. The numerical simulation results show that the well-trained neural network can recover internal structure in sinogram domain and improves image quality by reconstructing complete projection data.