Progressive self-supervised blind-spot denoising method for LDCT denoising
This addresses the problem of acquiring paired training data for medical imaging denoising, offering a practical solution for clinical applications, though it is incremental in self-supervised learning.
The paper tackles low-dose CT image denoising by proposing a self-supervised method that uses only LDCT images, eliminating the need for paired normal-dose data, and achieves performance comparable to or better than supervised methods on the Mayo LDCT dataset.
Self-supervised learning is increasingly investigated for low-dose computed tomography (LDCT) image denoising, as it alleviates the dependence on paired normal-dose CT (NDCT) data, which are often difficult to acquire in clinical practice. In this paper, we propose a novel self-supervised training strategy that relies exclusively on LDCT images. We introduce a step-wise blind-spot denoising mechanism that enforces conditional independence in a progressive manner, enabling more fine-grained denoising learning. In addition, we add Gaussian noise to LDCT images, which acts as a regularization and mitigates overfitting. Extensive experiments on the Mayo LDCT dataset demonstrate that the proposed method consistently outperforms existing self-supervised approaches and achieves performance comparable to, or better than, several representative supervised denoising methods.