Abstract:
To develop and assess a deep learning (DL) pipeline to learn dynamic MR image reconstruction from publicly available natural videos (Inter4K). Learning was performed for a range of DL architectures (VarNet, 3D UNet, FastDVDNet) and corresponding sampling patterns (Cartesian, radial, spiral) either from true multi-coil cardiac MR data (N = 692) or from synthetic MR data simulated from Inter4K natural videos (N = 588). Real-time undersampled dynamic MR images were reconstructed using DL networks trained with cardiac data and natural videos, and compressed sensing (CS). Differences were assessed in simulations (N = 104 datasets) in terms of MSE, PSNR, and SSIM and prospectively for cardiac cine (short axis, four chambers, N = 20) and speech cine (N = 10) data in terms of subjective image quality ranking, SNR and Edge sharpness. Friedman Chi Square tests with post-hoc Nemenyi analysis were performed to assess statistical significance. In simulated data, DL networks trained with cardiac data outperformed DL networks trained with natural videos, both of which outperformed CS (p < 0.05). However, in prospective experiments DL reconstructions using both training datasets were ranked similarly (and higher than CS) and presented no statistical differences in SNR and Edge Sharpness for most conditions.The developed pipeline enabled learning dynamic MR reconstruction from natural videos preserving DL reconstruction advantages such as high quality fast and ultra-fast reconstructions while overcoming some limitations (data scarcity or sharing). The natural video dataset, code and pre-trained networks are made readily available on github.
摘要:
开发和评估深度学习(DL)管道,以从公开可用的自然视频(Inter4K)中学习动态MR图像重建。对一系列DL架构进行了学习(VarNet,3DUNet,FastDVDNet)和相应的采样模式(笛卡尔,径向,螺旋)来自真实的多线圈心脏MR数据(N=692)或从Inter4K自然视频(N=588)模拟的合成MR数据。使用用心脏数据和自然视频训练的DL网络重建实时欠采样动态MR图像,和压缩感知(CS)。在模拟(N=104个数据集)中评估了MSE的差异,PSNR,和SSIM,以及心脏电影的前瞻性(短轴,四个房间,N=20)和语音电影(N=10)数据在主观图像质量排名方面,SNR和边缘锐度。使用事后Nemenyi分析进行弗里德曼卡方检验以评估统计学意义。在模拟数据中,用心脏数据训练的DL网络优于用自然视频训练的DL网络,两者均优于CS(p<0.05)。然而,在前瞻性实验中,使用两种训练数据集的DL重建进行了类似的排名(并且高于CS),并且在大多数条件下在SNR和边缘锐度方面没有统计学差异。开发的管道能够从自然视频中学习动态MR重建,保留了DL重建优势,例如高质量的快速和超快重建,同时克服了一些限制(数据稀缺或共享)。自然视频数据集,代码和预先训练的网络在github上很容易获得。