Adversarial and Score-Based CT Denoising: CycleGAN vs Noise2Score

TL;DR

This paper compares CycleGAN and Noise2Score methods for CT image denoising in unpaired and self-supervised settings, showing CycleGAN achieves higher image quality while Noise2Score offers a robust alternative when clean data is unavailable.

Contribution

It provides a comprehensive evaluation of CycleGAN and Noise2Score for CT denoising, identifying optimal configurations and comparing their performance in a common framework.

Findings

CycleGAN improves PSNR and SSIM significantly over noisy inputs.

CycleGAN achieves higher final image quality than Noise2Score.

Noise2Score performs well on very noisy inputs, especially without clean training data.

Abstract

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.