Region-of-interest undersampled MRI reconstruction: A deep convolutional neural network approach
作者: Liyan SunZhiwen FanXinghao DingYue HuangJohn Paisley
作者单位: 1Fujian Key Laboratory of Sensing and Computing for Smart City, Xiamen University, Fujian, China
2Department of Electrical Engineering, Columbia University, New York, NY, USA
刊名: Magnetic Resonance Imaging, 2019, Vol.63 , pp.185-192
来源数据库: Elsevier Journal
DOI: 10.1016/j.mri.2019.07.010
关键词: Deep convolutional neural networkMagnetic resonance imagingImage reconstructionRegion of interest
原始语种摘要: Abstract(#br)Compressive sensing enables fast magnetic resonance imaging (MRI) reconstruction with undersampled k-space data. However, in most existing MRI reconstruction models, the whole MR image is targeted and reconstructed without taking specific tissue regions into consideration. This may fails to emphasize the reconstruction accuracy on important and region-of-interest (ROI) tissues for diagnosis. In some ROI-based MRI reconstruction models, the ROI mask is extracted by human experts in advance, which is laborious when the MRI datasets are too large. In this paper, we propose a deep neural network architecture for ROI MRI reconstruction called ROIRecNet to improve reconstruction accuracy of the ROI regions in under-sampled MRI. In the model, we obtain the ROI masks by feeding an...
全文获取路径: Elsevier  (合作)
影响因子:2.06 (2012)

  • reconstruction 复原
  • undersampled 欠抽样的
  • network 网络
  • convolutional 卷积
  • neural 神经系统的
  • interest 兴趣
  • ROI 感兴趣区
  • reconstructed 修]重构[建
  • MRI Machine-Readable Information
  • segmentation 分段