利用频率域特性自监督生成伪样本，实现低剂量CT去噪
FrequencyCT: Frequency Domain Self-supervised Low-dose CT Denoising
- 在频率域通过低频锚定区分噪声与信号，生成伪样本
- 基于噪声方差与信号的指数相关性，稳定优化梯度
- 无需配对数据，适合临床真实场景应用
尽管计算断层扫描（CT）去噪研究广泛开展，但很少有工作利用投影域数据特征来缓解噪声相关性。为此，本文提出FrequencyCT，首个零样本自监督方法，在频率域生成伪样本用于低剂量CT去噪。通过利用噪声与真实信号在频率域的分布差异，提出区域低频锚定技术；对高频区域施加保持相位的噪声和掩码扰动，生成用于自监督的伪样本。基于噪声投影方差与潜在真实信号之间的指数相关性，对生成样本实施一致的数据截断，以稳定优化梯度。在多个公开及真实数据集上的评估结果验证了该方法的临床应用潜力，为去噪领域提供了新视角。代码已开源：https://github.com/yqx7150/FrequencyCT。
原文摘要 · Abstract (English)
Despite extensive research on computed tomography (CT) denoising, few studies exploit projection-domain data characteristics to mitigate noise correlation. To bridge this gap, this work proposes FrequencyCT, the first zero-shot self-supervised method for pseudo-sample generation in the frequency domain for low-dose CT denoising. Specifically, by exploiting the distinct frequency-domain distributions of noise and true signal, a regional low-frequency anchoring technique is proposed. Applying phase-preserving noise and mask perturbations to the high-frequency region generates pseudo-samples for self-supervision. Driven by the exponential correlation between noise variance of noisy projections and the underlying true signal, consistent data truncation is applied to the generated samples to stabilize optimization gradients. Evaluation results on multiple public and real datasets confirm the clinical application potential of this research, which provides an innovative perspective for the field of denoising. The code is available at: https://github.com/yqx7150/FrequencyCT.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。