The LoDoPaB-CT Dataset: A Benchmark Dataset for Low-Dose CT Reconstruction Methods

In this case we used the Ram-Lak filter. If the measurements are noisy, FBP reconstructions tend to include streaking artifacts. A typical approach to overcome this problem is to apply some kind of post-processing such as denoising. Recent works [9, 18, 37] have successfully used convolutional neural networks, such as the U-Net [29]. The idea is to train a neural network to create clean reconstructions out of the noisy FBP results. In our implementation we used a U-Net-like architecture which is shown in Figure 4 and is similar to the one used in [21]. There, the authors show that such an architecture is a good image prior, i.e., its output is biased towards natural images, for example, noise-free images. Training was performed by minimizing the mean squared error loss with the Adam algorithm [20] for 20 epochs with batch size 64 and learning rate starting at 0 .01