Adversarial and Score-Based CT Denoising: CycleGAN vs Noise2Score
This work addresses CT image denoising for medical imaging applications, providing an incremental comparison of existing methods.
The paper tackles CT image denoising in unpaired and self-supervised settings by comparing CycleGAN and Noise2Score methods, finding that CycleGAN with a U-Net backbone improves noisy input from 34.66 dB/0.9234 SSIM to 38.913 dB/0.971 SSIM, while Noise2Score offers robust pair-free denoising with competitive performance.
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.