Dose-aware adaptive denoising network for low-dose CT

Low-dose computed tomography (LDCT) for reducing the radiation dose to the patient is an important topic in the medical imaging field. To improve the quality of image reconstructed via LDCT, several deep learning (DL)-based methods have been suggested. However, those approaches often require sufficient pairs of LDCT and normal-dose CT (NDCT) images, which are difficult to acquire in clinical practice. On the other hand, most existing DL-based methods suffer from generalization issues because the network is trained with one or a few specific dose levels. To overcome the aforementioned problems, we propose a novel denoising framework that can be easily generalized to various dose levels while using only NDCT images. Furthermore, we mathematically derive a noise-variance calibration module for network training to handle the over-smoothing in network’s output. Once the network is trained, we can adaptively reduce the noise in the test LDCT images of different doses. The proposed method shows superior performance in preserving noise textures while achieving the best scores in the quantitative assessment that evaluates perceptual quality.