FrequencyCT: Frequency domain pseudo-label generation for self-supervised low-dose CT denoising
This work addresses noise correlation in CT denoising by leveraging frequency-domain characteristics, offering a novel approach for self-supervised denoising without requiring paired training data.
FrequencyCT introduces the first zero-shot self-supervised method for low-dose CT denoising that generates pseudo-labels in the frequency domain, achieving clinical application potential on multiple datasets.
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.