改进GAN模型提升高分辨率MRI图像质量，减少噪声与伪影。
Optimisation of SOUP-GAN and CSR-GAN for High Resolution MR Images Reconstruction
- 通过加深网络结构、优化激活函数与超参数，增强生成器与判别器性能。
- CSR-GAN在高频细节重建上表现更优，PSNR达34.6，SSIM达0.89。
- SOUP-GAN生成图像更清晰，噪声更低，适合结构保持要求高的场景。
磁共振成像（MRI）是现代医学中常用的诊断工具，但其图像质量易受运动伪影影响，且受限于设备性能。本研究聚焦于使用两种高效生成对抗网络（GAN）模型——SOUP-GAN和CSR-GAN——提升MRI图像质量。对两个模型的生成器与判别器均引入有意义的架构改进，通过增加卷积层并扩大滤波器尺寸，同时采用LeakyReLU激活函数改善梯度流动，并应用学习率降低与最优批次大小等超参数调优策略。此外，提出谱归一化以缓解模式崩溃，提升训练稳定性。实验表明，CSR-GAN在重建高频细节和降噪方面表现更佳，优化后达到PSNR 34.6、SSIM 0.89；而SOUP-GAN在保持图像结构的同时产生更少噪声，实现PSNR 34.4、SSIM 0.83。结果表明，所提出的增强型GAN模型可有效提升MRI图像质量，助力后续疾病诊断。
原文摘要 · Abstract (English)
Magnetic Resonance (MR) imaging is a diagnostic tool used in modern medicine; however, its output can be affected by motion artefacts and may be limited by equipment. This research focuses on MRI image quality enhancement using two efficient Generative Adversarial Networks (GANs) models: SOUP-GAN and CSR-GAN. In both models, meaningful architectural modifications were introduced. The generator and discriminator of each were further deepened by adding convolutional layers and were enhanced in filter sizes as well. The LeakyReLU activation function was used to improve gradient flow, and hyperparameter tuning strategies were applied, including a reduced learning rate and an optimal batch size. Moreover, spectral normalisation was proposed to address mode collapse and improve training stability. The experiment shows that CSR-GAN has better performance in reconstructing the image with higher frequency details and reducing noise compared to other methods, with an optimised PSNR of 34.6 and SSIM of 0.89. However, SOUP-GAN performed the best in terms of delivering less noisy images with good structures, achieving a PSNR of 34.4 and SSIM of 0.83. The obtained results indicate that the proposed enhanced GAN model can be a useful tool for MR image quality improvement for subsequent better disease diagnostics.
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。