arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1812.08155cs.CV
收藏

基于循环神经网络的磁共振指纹识别

Magnetic Resonance Fingerprinting using Recurrent Neural Networks

Guys & St Thomas NHS Foundation Trust(盖伊和圣托马斯国民保健服务基金会信托);Kings College Hospital NHS Foundation Trust(国王学院医院国民保健服务基金会信托)

Ilkay Oksuz, Gastao Cruz, James Clough, Aurelien Bustin, Nicolo Fuin, Rene M. Botnar, Claudia Prieto, Andrew P. King, Julia A. Schnabel

摘要:

磁共振指纹(MRF)是一种新的定量磁共振成像方法,允许在一个单一的,时间效率高的采集同时测量多种组织特性。标准MRF使用字典匹配来重建参数映射,并且由于计算效率低而缺乏可扩展性。我们建议使用递归神经网络进行MRF映射重建,该网络利用MRF信号演化的时间相关信息。我们评估我们的方法多参数合成信号,并将其与现有的MRF地图重建方法,包括那些基于神经网络。我们的方法实现了T1和T2值的最新估计。此外,与基于字典匹配的方法相比,重建时间显著减少。

英文摘要:

Magnetic Resonance Fingerprinting (MRF) is a new approach to quantitative magnetic resonance imaging that allows simultaneous measurement of multiple tissue properties in a single, time-efficient acquisition. Standard MRF reconstructs parametric maps using dictionary matching and lacks scalability due to computational inefficiency. We propose to perform MRF map reconstruction using a recurrent neural network, which exploits the time-dependent information of the MRF signal evolution. We evaluate our method on multiparametric synthetic signals and compare it to existing MRF map reconstruction approaches, including those based on neural networks. Our method achieves state-of-the-art estimates of T1 and T2 values. In addition, the reconstruction time is significantly reduced compared to dictionary-matching based approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑