A feature-based convolutional neural network for reconstruction of interventional MRI,NMR in Biomedicine

当前位置： X-MOL 学术 › NMR Biomed. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

A feature-based convolutional neural network for reconstruction of interventional MRI
NMR in Biomedicine ( IF 2.7 ) Pub Date : 2019-12-19 , DOI: 10.1002/nbm.4231
Blanca Zufiria _{1,

2} , Suhao Qiu ₁ , Kang Yan ₁ , Ruiyang Zhao ₁ , Runke Wang ₁ , Huajun She ₁ , Chengcheng Zhang ₃ , Bomin Sun ₃ , Pawel Herman ₄ , Yiping Du ₁ , Yuan Feng ₁

Affiliation

Real-time interventional MRI (I-MRI) could help to visualize the position of the interventional feature, thus improving patient outcomes in MR-guided neurosurgery. In particular, in deep brain stimulation, real-time visualization of the intervention procedure using I-MRI could improve the accuracy of the electrode placement. However, the requirements of a high undersampling rate and fast reconstruction speed for real-time imaging pose a great challenge for reconstruction of the interventional images. Based on recent advances in deep learning (DL), we proposed a feature-based convolutional neural network (FbCNN) for reconstructing interventional images from golden-angle radially sampled data. The method was composed of two stages: (a) reconstruction of the interventional feature and (b) feature refinement and postprocessing. With only five radially sampled spokes, the interventional feature was reconstructed with a cascade CNN. The final interventional image was constructed with a refined feature and a fully sampled reference image. With a comparison of traditional reconstruction techniques and recent DL-based methods, it was shown that only FbCNN could reconstruct the interventional feature and the final interventional image. With a reconstruction time of ~ 500 ms per frame and an acceleration factor of ~ 80, it was demonstrated that FbCNN had the potential for application in real-time I-MRI.

中文翻译：

一种基于特征的卷积神经网络重建介入MRI

实时介入 MRI (I-MRI) 可以帮助可视化介入特征的位置，从而改善 MR 引导的神经外科手术的患者预后。特别是在深部脑刺激中，使用 I-MRI 对干预过程进行实时可视化可以提高电极放置的准确性。然而，实时成像对高欠采样率和快速重建速度的要求对介入图像的重建提出了很大的挑战。基于深度学习 (DL) 的最新进展，我们提出了一种基于特征的卷积神经网络 (FbCNN)，用于从黄金角度径向采样数据中重建介入图像。该方法由两个阶段组成：（a）介入特征的重建和（b）特征细化和后处理。只有五个径向采样的辐条，介入特征是用级联 CNN 重建的。最终的介入图像由精细的特征和完全采样的参考图像构成。通过比较传统的重建技术和最近的基于 DL 的方法，表明只有 FbCNN 可以重建介入特征和最终的介入图像。每帧的重建时间约为 500 毫秒，加速因子约为 80，证明 FbCNN 具有在实时 I-MRI 中应用的潜力。结果表明，只有 FbCNN 可以重建介入特征和最终的介入图像。每帧的重建时间约为 500 毫秒，加速因子约为 80，证明 FbCNN 具有在实时 I-MRI 中应用的潜力。结果表明，只有 FbCNN 可以重建介入特征和最终的介入图像。每帧的重建时间约为 500 毫秒，加速因子约为 80，证明 FbCNN 具有在实时 I-MRI 中应用的潜力。

更新日期：2019-12-19

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11