Transformer架构让极低信噪比的MRI图像也能清晰可用
Imaging Transformer for MRI Denoising: a Scalable Model Architecture that enables SNR << 1 Imaging
- 用三个注意力模块捕捉图像长程相关性与局部信息
- 在SNR低至0.2时仍能恢复清晰解剖结构，保持图像质量
- 适合心血管MRI等对精度要求高的临床场景
目的：提出一种灵活可扩展的成像Transformer（IT）架构，包含三个注意力模块，用于多维影像数据，应用于极低输入信噪比（SNR）下的MRI去噪。方法：设计了空间局部、空间全局和帧注意力三个独立模块，捕捉长程信号相关性并保留图像局部信息。采用注意力单元块处理5维张量（[B, C, F, H, W]），适配2D、2D+T及3D图像数据。构建基于HRNet的主干网络以容纳IT模块。训练集包含206,677个动态电影序列，测试集含7,267个序列。测试了10种输入SNR水平（0.05至8.0）。与七种卷积及Transformer基线模型对比。为验证可扩展性，训练了参数量从27M到218M的四个IT模型。两名资深心脏病专家评估模型输出的射血分数（EF），并与真实值比较。结果：IT模型在所有测试SNR下均显著优于其他模型，尤其在低SNR时优势明显。IT-218m模型在低至SNR 0.2时仍保持最高SSIM和PSNR，恢复出良好图像质量和解剖细节。当SNR≥0.2时，两位专家认为模型输出与真实图像具相同临床解读。模型生成图像的EF测量值与真实值高度一致。结论：成像Transformer在MR去噪中表现出强性能、良好可扩展性与通用性，可在极低输入信噪比（如0.2）下恢复出可供临床自信读片且支持精确EF测量的图像质量。
原文摘要 · Abstract (English)
Purpose: To propose a flexible and scalable imaging transformer (IT) architecture with three attention modules for multi-dimensional imaging data and apply it to MRI denoising with very low input SNR. Methods: Three independent attention modules were developed: spatial local, spatial global, and frame attentions. They capture long-range signal correlation and bring back the locality of information in images. An attention-cell-block design processes 5D tensors ([B, C, F, H, W]) for 2D, 2D+T, and 3D image data. A High Resolution (HRNet) backbone was built to hold IT blocks. Training dataset consists of 206,677 cine series and test datasets had 7,267 series. Ten input SNR levels from 0.05 to 8.0 were tested. IT models were compared to seven convolutional and transformer baselines. To test scalability, four IT models 27m to 218m parameters were trained. Two senior cardiologists reviewed IT model outputs from which the EF was measured and compared against the ground-truth. Results: IT models significantly outperformed other models over the tested SNR levels. The performance gap was most prominent at low SNR levels. The IT-218m model had the highest SSIM and PSNR, restoring good image quality and anatomical details even at SNR 0.2. Two experts agreed at this SNR or above, the IT model output gave the same clinical interpretation as the ground-truth. The model produced images that had accurate EF measurements compared to ground-truth values. Conclusions: Imaging transformer model offers strong performance, scalability, and versatility for MR denoising. It recovers image quality suitable for confident clinical reading and accurate EF measurement, even at very low input SNR of 0.2.
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。