Literature DB >> 30666723

Parallel imaging in time-of-flight magnetic resonance angiography using deep multistream convolutional neural networks.

Yohan Jun1, Taejoon Eo1, Hyungseob Shin1, Taeseong Kim1, Ho-Joon Lee2,3, Dosik Hwang1.   

Abstract

PURPOSE: To develop and evaluate a method of parallel imaging time-of-flight (TOF) MRA using deep multistream convolutional neural networks (CNNs).
METHODS: A deep parallel imaging network ("DPI-net") was developed to reconstruct 3D multichannel MRA from undersampled data. It comprises 2 deep-learning networks: a network of multistream CNNs for extracting feature maps of multichannel images and a network of reconstruction CNNs for reconstructing images from the multistream network output feature maps. The images were evaluated using normalized root mean square error (NRMSE), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) values, and the visibility of blood vessels was assessed by measuring the vessel sharpness of middle and posterior cerebral arteries on axial maximum intensity projection (MIP) images. Vessel sharpness was compared using paired t tests, between DPI-net, 2 conventional parallel imaging methods (SAKE and ESPIRiT), and a deep-learning method (U-net).
RESULTS: DPI-net showed superior performance in reconstructing vessel signals in both axial slices and MIP images for all reduction factors. This was supported by the quantitative metrics, with DPI-net showing the lowest NRMSE, the highest PSNR and SSIM (except R = 3.8 on sagittal MIP images, and R = 5.7 on axial slices and sagittal MIP images), and significantly higher vessel sharpness values than the other methods.
CONCLUSION: DPI-net was effective in reconstructing 3D TOF MRA from highly undersampled multichannel MR data, achieving superior performance, both quantitatively and qualitatively, over conventional parallel imaging and other deep-learning methods.
© 2019 International Society for Magnetic Resonance in Medicine.

Keywords:  deep-learning; magnetic resonance angiography; multistream network; parallel imaging; time-of-flight

Mesh:

Year:  2019        PMID: 30666723     DOI: 10.1002/mrm.27656

Source DB:  PubMed          Journal:  Magn Reson Med        ISSN: 0740-3194            Impact factor:   4.668


  3 in total

1.  Resting-state magnetoencephalography source magnitude imaging with deep-learning neural network for classification of symptomatic combat-related mild traumatic brain injury.

Authors:  Ming-Xiong Huang; Charles W Huang; Deborah L Harrington; Ashley Robb-Swan; Annemarie Angeles-Quinto; Sharon Nichols; Jeffrey W Huang; Lu Le; Carl Rimmele; Scott Matthews; Angela Drake; Tao Song; Zhengwei Ji; Chung-Kuan Cheng; Qian Shen; Ericka Foote; Imanuel Lerman; Kate A Yurgil; Hayden B Hansen; Robert K Naviaux; Robert Dynes; Dewleen G Baker; Roland R Lee
Journal:  Hum Brain Mapp       Date:  2021-01-15       Impact factor: 5.038

Review 2.  [The Latest Trends in Attention Mechanisms and Their Application in Medical Imaging].

Authors:  Hyungseob Shin; Jeongryong Lee; Taejoon Eo; Yohan Jun; Sewon Kim; Dosik Hwang
Journal:  Taehan Yongsang Uihakhoe Chi       Date:  2020-11-30

3.  Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI.

Authors:  Nobuo Kashiwagi; Hisashi Tanaka; Yuichi Yamashita; Hiroto Takahashi; Yoshimori Kassai; Masahiro Fujiwara; Noriyuki Tomiyama
Journal:  Acta Radiol Open       Date:  2021-06-18
  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.