FrequencyCT: Frequency domain pseudo-label generation for self-supervised low-dose CT denoising

TL;DR

FrequencyCT introduces a novel zero-shot self-supervised frequency domain method for low-dose CT denoising, effectively utilizing projection data characteristics to improve noise reduction without requiring paired training data.

Contribution

This work is the first to exploit projection-domain frequency characteristics for pseudo-label generation in self-supervised low-dose CT denoising.

Findings

Effective noise suppression demonstrated on multiple datasets.

Stable network training achieved through sample truncation.

Potential for clinical application confirmed.

Abstract

Despite extensive research on computed tomography (CT) denoising, few studies exploit projection-domain data characteristics to mitigate noise correlation. To address this, this work proposes FrequencyCT, the first zero-shot self-supervised method for pseudo-label generation in the frequency domain for low-dose CT denoising. Leveraging the characteristic of the frequency domain that largely isolates noise from clean signals, a regional low-frequency anchoring technique is proposed. Phase-preserving amplitude modulation and mask perturbation in the high-frequency region generate pseudo-label data for self-supervision. The fluctuating noise variance in the projection domain prompts truncation of the generated samples to stabilize the network's optimization gradient. Evaluation results on multiple public and real-world datasets confirm the clinical application potential of this research, which will have a revolutionary impact on the field of denoising. The code can be obtained from https://github.com/yqx7150/FrequencyCT.