Adversarial and Score-Based CT Denoising: CycleGAN vs Noise2Score
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 6 of its 10 references that are in the map. First posted on arXiv 6 Nov 2025.
Builds on
6 of 10 references.
References · 6
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
- 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
- 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 110
- 2020AR-DAE: Towards Unbiased Neural Entropy Gradient Estimationcited by 19
Built on by
Not cited yet.