Estimation of Cerebral Blood Flow and Arterial Transit Time From Multi‐Delay Arterial Spin Labeling <scp>MRI</scp> Using a Simulation‐Based Supervised Deep Neural Network

  • Shota Ishida
    Department of Radiological Technology, Faculty of Medical Sciences Kyoto College of Medical Science Kyoto Japan
  • Makoto Isozaki
    Department of Neurosurgery, Division of Medicine, Faculty of Medical Sciences University of Fukui Fukui Japan
  • Yasuhiro Fujiwara
    Department of Medical Image Sciences, Faculty of Life Sciences Kumamoto University Kumamoto Japan
  • Naoyuki Takei
    GE Healthcare Tokyo Japan
  • Masayuki Kanamoto
    Radiological Center University of Fukui Hospital Fukui Japan
  • Hirohiko Kimura
    Faculty of Medical Sciences University of Fukui Fukui Japan
  • Tetsuya Tsujikawa
    Department of Radiology, Faculty of Medical Sciences University of Fukui Fukui Japan

抄録

<jats:sec><jats:title>Background</jats:title><jats:p>An inherently poor signal‐to‐noise ratio (SNR) causes inaccuracy and less precision in cerebral blood flow (CBF) and arterial transit time (ATT) when using arterial spin labeling (ASL). Deep neural network (DNN)‐based parameter estimation can solve these problems.</jats:p></jats:sec><jats:sec><jats:title>Purpose</jats:title><jats:p>To reduce the effects of Rician noise on ASL parameter estimation and compute unbiased CBF and ATT using simulation‐based supervised DNNs.</jats:p></jats:sec><jats:sec><jats:title>Study Type</jats:title><jats:p>Retrospective.</jats:p></jats:sec><jats:sec><jats:title>Population</jats:title><jats:p>One million simulation test data points, 17 healthy volunteers (five women and 12 men, 33.2 ± 14.6 years of age), and one patient with moyamoya disease.</jats:p></jats:sec><jats:sec><jats:title>Field Strength/Sequence</jats:title><jats:p>3.0 T/Hadamard‐encoded pseudo‐continuous <jats:styled-content style="fixed-case">ASL</jats:styled-content> with a three‐dimensional fast spin‐echo stack of spirals.</jats:p></jats:sec><jats:sec><jats:title>Assessment</jats:title><jats:p>Performances of DNN and conventional methods were compared. For test data, the normalized mean absolute error (NMAE) and normalized root mean squared error (NRMSE) between the ground truth and predicted values were evaluated. For in vivo data, baseline CBF and ATT and their relative changes with respect to SNR using artificial noise‐added images were assessed.</jats:p></jats:sec><jats:sec><jats:title>Statistical Tests</jats:title><jats:p>One‐way analysis of variance with post‐hoc Tukey's multiple comparison test, paired <jats:italic>t</jats:italic>‐test, and the Bland–Altman graphical analysis. Statistical significance was defined as <jats:italic>P</jats:italic> < 0.05.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>For both CBF and ATT, NMAE and NRMSE were lower with DNN than with the conventional method. The baseline values were significantly smaller with DNN than with the conventional method (CBF in gray matter, 66 ± 10 vs. 71 ± 12 mL/100 g/min; white matter, 45 ± 6 vs. 46 ± 7 mL/100 g/min; ATT in gray matter, 1424 ± 201 vs. 1471 ± 154 msec). CBF and ATT increased with decreasing SNR; however, their change rates were smaller with DNN than were those with the conventional method. Higher CBF in the prolonged ATT region and clearer contrast in ATT were identified by DNN in a clinical case.</jats:p></jats:sec><jats:sec><jats:title>Data Conclusion</jats:title><jats:p>DNN outperformed the conventional method in terms of accuracy, precision, and noise immunity.</jats:p><jats:p>Evidence Level: 3</jats:p><jats:p>Technical Efficacy: Stage 1</jats:p></jats:sec>

収録刊行物

参考文献 (40)*注記

もっと見る

関連プロジェクト

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ