文献速递神经MR

生成式AI去噪加速7T梯度回波脑MRI

Accelerating 7T Gradient-Echo Brain MRI With Generative AI Denoising.
PubMed 文献 · Acad Radiol · 2026-09-26

本研究训练7T条件扩散模型,利用多次重复采集图像作为参考,对短时2D T2加权梯度回波图像去噪。模型在19名受试者中测试,在MSE、PSNR、SSIM上均优于CNN、ViT和GAN模型。专家评分显示海马、白质病变及皮层小静脉细节与对比度保持更好。

要点

  • 7T条件扩散模型去噪后图像更接近多次重复采集参考标准
  • 短时扫描去噪可提高临床7T检查的可行性
  • 去噪对海马、白质病变和小皮层静脉细节保持良好

核心结论

  • 生成式AI去噪可从短时扫描获得高质量图像,缩短患者扫描时间同时保持解剖和病理细节

研究设计与样本

  • 研究训练7T条件扩散模型,使用内部7T数据集共11次检查,包含多次重复2D T2加权梯度回波采集
  • 模型以单次采集2D重建为输入,以多次重复图像为参考进行去噪并增强信噪比与对比度
  • 测试集为19名受试者的2D T2加权梯度回波图像,包括8名健康对照、6名轻度认知障碍、5名阿尔茨海默病
  • 对照模型包括未处理的单次采集重建以及类似训练的卷积神经网络、视觉Transformer和生成对抗网络

关键影像表现/征象

  • 去噪后海马、白质病变和小皮层静脉的细节显著增强且对比度保持

诊断标准与关键数值

  • 以多次重复采集为参考标准,7T条件扩散模型使单次采集原始图像MSE改善31.7%,PSNR改善4.9%,SSIM改善7.5%
  • 在所有指标上7T条件扩散模型均优于其他所有模型,P<0.001
  • 专家评分显示去噪图像细节增强P<0.001,对比度保持P<0.001

临床应用与阅片要点

  • 对短时7T脑MRI图像可用生成式AI去噪以提升信噪比和对比度,缩短检查时间
  • 阅片时需关注去噪对海马、白质病变和小静脉等结构细节的影响

局限性

  • 原文未提供样本量之外的局限信息

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: This study aimed to efficiently denoise short 7 T MRI acquisitions to achieve the image quality of longer scans using a generative Artificial Intelligence (AI) model.

MATERIALS AND METHODS: A 7T Conditional Diffusion Model (7TCDM) was trained on an in-house 7T dataset of 11 examinations consisting of multi-repetition 2D T2-weighted gradient-echo acquisitions. The model utilized native single-acquisition 2D reconstructions, using multi-repetition images as a reference to guide denoising and enhance signal-to-noise ratio and contrast. Performance was compared to the same single-acquisition reconstruction either unprocessed or enhanced by a similarly trained convolutional neural network, vision transformer, and generative adversarial network, using Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and comprehensive neuroradiologic ratings.

RESULTS: 7TCDM was tested on 2D T2-weighted gradient-echo images from 19 participants: eight healthy controls, six individuals with mild cognitive impairment, and five with Alzheimer's disease. Referencing the multi-repetition reference standard, 7TCDM improved the single-acquisition original image by 31.7% in MSE, 4.9% in PSNR, and 7.5% in SSIM, outperforming all other models in all metrics (P < 0.001). Expert rater evaluations confirmed superior image quality, with significantly enhanced detail (P < 0.001) and contrast preservation (P < 0.001) for the hippocampi, for white matter lesions, and for small cortical veins.

CONCLUSIONS: Generative AI denoising provides high-quality denoised images from shorter scans, increasing the feasibility of scanning patients in shorter times while preserving essential anatomical and pathological details.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Wang, Li, Liang, et al. Accelerating 7T Gradient-Echo Brain MRI With Generative AI Denoising. Acad Radiol. 2026. PMID: 42800791. doi:10.1016/j.acra.2026.09.011

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。