基于深度学习的MRI加速:当前格局与神经放射学临床应用
综述探讨基于深度学习的图像重建(DLBIR)在神经影像中的应用,可减少扫描时间并保持或改善图像质量,但存在跨设备泛化性、伪影易感性及病理表现改变等挑战,且厂商闭源算法训练数据与临床验证有限。
要点
- DLBIR可在保持或改善图像质量的同时减少扫描时间,厂商声称梯度时间缩减可达85%。
- DLBIR从2D向3D采集演进,结合自监督学习进一步扩展能力与临床适用性。
- 厂商闭源算法的训练数据、底层算法与临床验证有限,影响用户信任与广泛采用。
核心结论
- DLBIR可通过多种方式减少扫描时间,同时保持或改善图像质量,并可能提高病灶显著性、噪声抑制和诊断准确性。
研究设计与样本
- 综述,探讨DLBIR在神经影像中的当前应用、厂商实现方式及新兴趋势。
关键影像表现/征象
- DLBIR可保持或增强病灶显著性,并改善噪声抑制。
诊断标准与关键数值
- 厂商声称梯度时间缩减可达85%,同时保持或增强病灶显著性、改善噪声抑制和诊断准确性。
临床应用与阅片要点
- DLBIR从2D向3D采集演进,结合自监督学习可进一步扩展其能力与临床适用性。
局限性
- 跨扫描仪和成像条件的泛化性存在挑战。
- 对伪影易感。
- 可能导致病理表现改变。
- 厂商闭源算法的训练数据、底层算法和临床验证数据有限。
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
MRI is a cornerstone of neuroimaging, providing unparalleled soft-tissue contrast. However, its clinical utility is often limited by long acquisition times, which contribute to motion artifacts, patient discomfort, and increased costs. Although traditional acceleration techniques, such as parallel imaging and compressed sensing help reduce scan times, they may reduce SNR and introduce artifacts. The advent of deep learning-based image reconstruction (DLBIR) may help in several ways to reduce scan times while preserving or improving image quality. Various DLBIR techniques are currently available through different vendors, with claimed reductions in gradient times up to 85% while maintaining or enhancing lesion conspicuity, improved noise suppression and diagnostic accuracy. The evolution of DLBIR from 2D to 3D acquisitions, coupled with advancements in self-supervised learning, further expands its capabilities and clinical applicability. Despite these advancements, challenges persist in generalizability across scanners and imaging conditions, susceptibility to artifacts, and potential alterations in pathology representation. Additionally, limited data on training, underlying algorithms, and clinical validation of these vendor-specific closed-source algorithms pose barriers to end-user trust and widespread adoption. This review explores the current applications of DLBIR in neuroimaging, vendor-driven implementations, and emerging trends that may impact accelerated MRI acquisitions.
引用
- Rai P, Mark IT, Soni N, et al. Deep Learning-Based Acceleration in MRI: Current Landscape and Clinical Applications in Neuroradiology. AJNR Am J Neuroradiol. 2026. PMID: 40721279. doi:10.3174/ajnr.A8943
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。