对比三种生成模型在脑部MRI T1转T2图像上的表现，助临床选型。
MRI Cross-Modal Synthesis: A Comparative Study of Generative Models for T1-to-T2 Reconstruction
- 用Pix2Pix GAN、CycleGAN和VAE实现T1到T2图像生成
- CycleGAN在PSNR（32.28 dB）和SSIM（0.9008）上最优
- VAE虽性能较低但具潜在可解释性与采样优势
MRI跨模态合成通过一种扫描协议生成另一种图像，具有显著临床价值，可缩短扫描时间并保留诊断信息。本文对三种先进生成模型——Pix2Pix GAN、CycleGAN和变分自编码器（VAE）——在T1到T2 MRI重建任务中进行综合比较。基于BraTS 2020数据集（训练切片11,439，测试切片2,000），采用均方误差（MSE）、峰值信噪比（PSNR）和结构相似性指数（SSIM）等指标评估性能。实验表明，所有模型均可成功从T1输入生成T2图像：CycleGAN达到最高PSNR（32.28 dB）和SSIM（0.9008），Pix2Pix GAN表现最低的MSE（0.005846），而VAE虽量化指标较差（MSE: 0.006949，PSNR: 24.95 dB，SSIM: 0.6573），但在潜在空间表示和采样方面具优势。本研究为研究人员和临床医生根据具体需求与数据条件选择合适生成模型提供了重要参考。
原文摘要 · Abstract (English)
MRI cross-modal synthesis involves generating images from one acquisition protocol using another, offering considerable clinical value by reducing scan time while maintaining diagnostic information. This paper presents a comprehensive comparison of three state-of-the-art generative models for T1-to-T2 MRI reconstruction: Pix2Pix GAN, CycleGAN, and Variational Autoencoder (VAE). Using the BraTS 2020 dataset (11,439 training and 2,000 testing slices), we evaluate these models based on established metrics including Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM). Our experiments demonstrate that all models can successfully synthesize T2 images from T1 inputs, with CycleGAN achieving the highest PSNR (32.28 dB) and SSIM (0.9008), while Pix2Pix GAN provides the lowest MSE (0.005846). The VAE, though showing lower quantitative performance (MSE: 0.006949, PSNR: 24.95 dB, SSIM: 0.6573), offers advantages in latent space representation and sampling capabilities. This comparative study provides valuable insights for researchers and clinicians selecting appropriate generative models for MRI synthesis applications based on their specific requirements and data constraints.
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。