Self-supervised noise2noise method utilizing corrupted images with a modular network for LDCT denoising

Deep learning is a very promising technique for low-dose computed tomography (LDCT) image denoising. However, traditional deep learning methods require paired noisy and clean datasets, which are often difficult to obtain. This paper proposes a new method for performing LDCT image denoising with only LDCT data, which eliminates the need for normal-dose CT (NDCT). We adopt a combination of the self-supervised noise2noise model and the noisy-as-clean strategy. First, we add a second yet similar type of noise to the LDCT images multiple times. Note that we use LDCT images instead of NDCT images based on the noisy-as-clean strategy for corruption. Then, the noise2noise model is executed using only the secondary corrupted images for training. We select a modular U-Net structure from several candidates with shared parameters to perform the task, which increases the receptive field without increasing the parameter size. The experimental results obtained on the Mayo LDCT dataset show the effectiveness of the proposed method compared with that of the state-of-the-art deep learning methods. The developed code is available at https://github.com/XYuan01/Self-supervised-Noise2Noise-for-LDCT.