对比两种无配对自监督去噪方法，提升低剂量CT图像质量。
Adversarial and Score-Based CT Denoising: CycleGAN vs Noise2Score
- 用CycleGAN残差转换器与Noise2Score分数匹配模型做无配对去噪
- CycleGAN将信噪比从34.66 dB提至38.913 dB，SSIM达0.971
- Noise2Score在极噪声下表现更优，适合无干净数据场景
我们评估了两种高效训练的无配对自监督去噪范式：基于CycleGAN的残差翻译器和Noise2Score（N2S）分数匹配去噪器。在统一评测协议下，通过配置搜索确定CycleGAN的最佳设置（lambda_cycle = 30, lambda_iden = 2, ngf = ndf = 64），并使用更长训练周期训练至收敛。该配置使噪声输入从34.66 dB / 0.9234 SSIM提升至38.913 dB / 0.971 SSIM，获得估计得分1.9441，未见集（Kaggle排行榜）得分为1.9343。尽管Noise2Score在绝对PSNR/SSIM上略逊，但在极噪声输入下显著优于基线，凸显其在缺乏干净配对数据时的实用性。总体而言，CycleGAN提供最佳图像质量，而Noise2Score则作为稳健的无配对替代方案，性能可比。
原文摘要 · Abstract (English)
We study CT image denoising in the unpaired and self-supervised regimes by evaluating two strong, training-data-efficient paradigms: a CycleGAN-based residual translator and a Noise2Score (N2S) score-matching denoiser. Under a common evaluation protocol, a configuration sweep identifies a simple standard U-Net backbone within CycleGAN (lambda_cycle = 30, lambda_iden = 2, ngf = ndf = 64) as the most reliable setting; we then train it to convergence with a longer schedule. The selected CycleGAN improves the noisy input from 34.66 dB / 0.9234 SSIM to 38.913 dB / 0.971 SSIM and attains an estimated score of 1.9441 and an unseen-set (Kaggle leaderboard) score of 1.9343. Noise2Score, while slightly behind in absolute PSNR / SSIM, achieves large gains over very noisy inputs, highlighting its utility when clean pairs are unavailable. Overall, CycleGAN offers the strongest final image quality, whereas Noise2Score provides a robust pair-free alternative with competitive performance. Source code is available at https://github.com/hanifsyarubany/CT-Scan-Image-Denoising-using-CycleGAN-and-Noise2Score.
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。