Combined Denoising and Suppression of Transient Artifacts in Arterial Spin LabelingMRIUsing Deep Learning
Combined Denoising and Suppression of Transient Artifacts in Arterial Spin LabelingMRIUsing Deep Learning
复制标题
DOI：
10.1002/jmri.27255
复制
发表时间：
2020-06-15
影响因子：
4.4
通讯作者：
A. Clark, Chris
中科院分区：
文献类型：
--
作者：
Hales, Patrick W.;Pfeuffer, Josef;A. Clark, Chris
背景动脉自旋标记(ASL)是一种测量脑血流量(CBF)的有用工具。然而，由于该技术的低信噪比(SNR)，需要多次重复，这导致延长了扫描时间并增加了对伪影的敏感性。目的提出一种基于深度学习的ASL图像瞬时伪影同时去噪和抑制算法。研究类型回顾。受试者131名儿童神经肿瘤科患者接受模型训练，11名健康成人受试者接受模型评估。场强/序列3T/具有3D梯度和自旋回波读出的伪连续和脉冲ASL。评估采用堆叠编码/解码卷积层的去噪自动编码器(DAE)模型。参考标准图像由10幅成对的ASL减影图像平均而成。该模型被训练成使用单一的减影图像来产生类似质量的灌注图像。与高斯和非局部均值(NLM)滤波器的性能进行了比较。评价指标包括CBF图像的信噪比、峰值信噪比(PSNR)和结构相似指数(SSIM)，并与参考标准进行比较。统计检验用于群体比较的单因素方差分析(ANOVA)检验。结果DAE模型是唯一与原始图像相比信噪比显著提高的模型(P<；0.05)，平均信噪比提高62%。DAE模型在抑制瞬变伪影方面也是有效的，并且是唯一一个显示生成的CBF图像的准确性显著提高的模型，使用PSNR值进行评估(P<；0.05)。此外，使用来自多次流入时间采集的数据，DAE图像产生了与Buxton动力学模型最匹配的结果，与原始图像相比，其拟合误差降低了75%。数据结论基于深度学习的算法在去除ASL图像噪声时具有较高的精度，因为它们能够同时提高信噪比和抑制原始ASL图像中的伪影信号。证据级别3技术功效阶段1
Background Arterial spin labeling (ASL) is a useful tool for measuring cerebral blood flow (CBF). However, due to the low signal-to-noise ratio (SNR) of the technique, multiple repetitions are required, which results in prolonged scan times and increased susceptibility to artifacts. Purpose To develop a deep-learning-based algorithm for simultaneous denoising and suppression of transient artifacts in ASL images. Study Type Retrospective. Subjects 131 pediatric neuro-oncology patients for model training and 11 healthy adult subjects for model evaluation. Field Strength/Sequence 3T / pseudo-continuous and pulsed ASL with 3D gradient-and-spin-echo readout. Assessment A denoising autoencoder (DAE) model was designed with stacked encoding/decoding convolutional layers. Reference standard images were generated by averaging 10 pairwise ASL subtraction images. The model was trained to produce perfusion images of a similar quality using a single subtraction image. Performance was compared against Gaussian and non-local means (NLM) filters. Evaluation metrics included SNR, peak SNR (PSNR), and structural similarity index (SSIM) of the CBF images, compared to the reference standard. Statistical Tests One-way analysis of variance (ANOVA) tests for group comparisons. Results The DAE model was the only model to produce a significant increase in SNR compared to the raw images (P < 0.05), providing an average SNR gain of 62%. The DAE model was also effective at suppressing transient artifacts, and was the only model to show a significant improvement in accuracy in the generated CBF images, as assessed using PSNR values (P < 0.05). In addition, using data from multiple inflow time acquisitions, the DAE images produced the best fit to the Buxton kinetic model, offering a 75% reduction in the fitting error compared to the raw images. Data Conclusion Deep-learning-based algorithms provide superior accuracy when denoising ASL images, due to their ability to simultaneously increase SNR and suppress artifactual signals in raw ASL images. Level of Evidence 3 Technical Efficacy Stage 1