Masked Autoencoders for Low dose CT denoising
This addresses the challenge of limited labeled data in clinical CT denoising, though it is incremental as it adapts an existing self-pretraining method to a specific domain.
The paper tackles the problem of low-dose CT denoising by redesigning masked autoencoders (MAE) to leverage unlabeled data, reducing reliance on paired noisy-clean data and improving transformer performance on the Mayo dataset.
Low-dose computed tomography (LDCT) reduces the X-ray radiation but compromises image quality with more noises and artifacts. A plethora of transformer models have been developed recently to improve LDCT image quality. However, the success of a transformer model relies on a large amount of paired noisy and clean data, which is often unavailable in clinical applications. In computer vision and natural language processing fields, masked autoencoders (MAE) have been proposed as an effective label-free self-pretraining method for transformers, due to its excellent feature representation ability. Here, we redesign the classical encoder-decoder learning model to match the denoising task and apply it to LDCT denoising problem. The MAE can leverage the unlabeled data and facilitate structural preservation for the LDCT denoising model when ground truth data are missing. Experiments on the Mayo dataset validate that the MAE can boost the transformer's denoising performance and relieve the dependence on the ground truth data.