用1.5T/3T MRI生成7T级脑部结构图，提升临床可及性
Generalizable 7T T1-map Synthesis from 1.5T and 3T T1 MRI with an Efficient Transformer Model
- 基于高效Transformer模型，从低场MRI重建高分辨率7T T1图
- 在1.5T输入下实现NMSE 0.019，较现有方法降低64%以上
- 适用于多场强数据混合训练，适合临床常规扫描设备升级
目的：7特斯拉（7T）MRI相比1.5T和3T标准场强具有更高的分辨率和对比度，但设备昂贵、稀缺且存在磁敏感伪影等挑战。本文提出一种基于高效Transformer的模型（7T-Restormer），从常规1.5T或3T T1加权（T1W）图像合成7T质量的T1图。方法：在35例1.5T与108例3T T1W图像配对的7T T1图患者数据上验证模型，共141例（32,128切片），随机划分为105例（25例1.5T + 80例3T）训练集（19,204切片）、19例（5例1.5T + 14例3T）验证集（3,476切片）和17例（5例1.5T + 14例3T）测试集（3,145切片）。合成结果与ResViT和ResShift模型比较。结果：7T-Restormer在1.5T输入下获得PSNR 26.0±4.6 dB、SSIM 0.861±0.072、NMSE 0.019±0.011；在3T输入下获得PSNR 25.9±4.9 dB、SSIM 0.866±0.077。仅使用1050万参数，相比5670万参数的ResShift（NMSE 0.052，p<.001）降低64%，相比7040万参数的ResViT（NMSE 0.032，p<.001）降低41%，3T场景同样表现更优（0.021 vs 0.060 和 0.033，p<.001）。混合1.5T+3T数据训练优于单一场强策略。仅训练1.5T数据使1.5T输入的NMSE升至0.021（p=1.1E-3），而仅训练3T则导致1.5T输入性能下降。结论：本方法可从1.5T和3T T1W扫描中预测定量7T MP2RAGE图，质量优于当前最先进方法，使7T MRI优势更易融入常规临床流程。
原文摘要 · Abstract (English)
Purpose: Ultra-high-field 7T MRI offers improved resolution and contrast over standard clinical field strengths (1.5T, 3T). However, 7T scanners are costly, scarce, and introduce additional challenges such as susceptibility artifacts. We propose an efficient transformer-based model (7T-Restormer) to synthesize 7T-quality T1-maps from routine 1.5T or 3T T1-weighted (T1W) images. Methods: Our model was validated on 35 1.5T and 108 3T T1w MRI paired with corresponding 7T T1 maps of patients with confirmed MS. A total of 141 patient cases (32,128 slices) were randomly divided into 105 (25; 80) training cases (19,204 slices), 19 (5; 14) validation cases (3,476 slices), and 17 (5; 14) test cases (3,145 slices) where (X; Y) denotes the patients with 1.5T and 3T T1W scans, respectively. The synthetic 7T T1 maps were compared against the ResViT and ResShift models. Results: The 7T-Restormer model achieved a PSNR of 26.0 +/- 4.6 dB, SSIM of 0.861 +/- 0.072, and NMSE of 0.019 +/- 0.011 for 1.5T inputs, and 25.9 +/- 4.9 dB, and 0.866 +/- 0.077 for 3T inputs, respectively. Using 10.5 M parameters, our model reduced NMSE by 64 % relative to 56.7M parameter ResShift (0.019 vs 0.052, p = <.001 and by 41 % relative to 70.4M parameter ResViT (0.019 vs 0.032, p = <.001) at 1.5T, with similar advantages at 3T (0.021 vs 0.060 and 0.033; p < .001). Training with a mixed 1.5 T + 3 T corpus was superior to single-field strategies. Restricting the model to 1.5T increased the 1.5T NMSE from 0.019 to 0.021 (p = 1.1E-3) while training solely on 3T resulted in lower performance on input 1.5T T1W MRI. Conclusion: We propose a novel method for predicting quantitative 7T MP2RAGE maps from 1.5T and 3T T1W scans with higher quality than existing state-of-the-art methods. Our approach makes the benefits of 7T MRI more accessible to standard clinical workflows.
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。