An unsupervised two‐step training framework for low‐dose computed tomography denoising

Abstract Background Although low‐dose computed tomography (CT) imaging has been more widely adopted in clinical practice to reduce radiation exposure to patients, the reconstructed CT images tend to have more noise, which impedes accurate diagnosis. Recently, deep neural networks using convolutional neural networks to reduce noise in the reconstructed low‐dose CT images have shown considerable improvement. However, they need a large number of paired normal‐ and low‐dose CT images to fully train the network via supervised learning methods. Purpose To propose an unsupervised two‐step training framework for image denoising that uses low‐dose CT images of one dataset and unpaired high‐dose CT images from another dataset. Methods Our proposed framework trains the denoising network in two steps. In the first training step, we train the network using 3D volumes of CT images and predict the center CT slice from them. This pre‐trained network is used in the second training step to train the denoising network and is combined with the memory‐efficient denoising generative adversarial network (DenoisingGAN), which further enhances both objective and perceptual quality. Results The experimental results on phantom and clinical datasets show superior performance over the existing traditional machine learning and self‐supervised deep learning methods, and the results are comparable to the fully supervised learning methods. Conclusions We proposed a new unsupervised learning framework for low‐dose CT denoising, convincingly improving noisy CT images from both objective and perceptual quality perspectives. Because our denoising framework does not require physics‐based noise models or system‐dependent assumptions, our proposed method can be easily reproduced; consequently, it can also be generally applicable to various CT scanners or dose levels.