Literature DB >> 34374468

Multiparametric mapping in the brain from conventional contrast-weighted images using deep learning.

Shihan Qiu1,2, Yuhua Chen1,2, Sen Ma1, Zhaoyang Fan1,3,4, Franklin G Moser5, Marcel M Maya5, Anthony G Christodoulou1,2, Yibin Xie1, Debiao Li1,2.   

Abstract

PURPOSE: To develop a deep-learning-based method to quantify multiple parameters in the brain from conventional contrast-weighted images.
METHODS: Eighteen subjects were imaged using an MR Multitasking sequence to generate reference T1 and T2 maps in the brain. Conventional contrast-weighted images consisting of T1 MPRAGE, T1 GRE, and T2 FLAIR were acquired as input images. A U-Net-based neural network was trained to estimate T1 and T2 maps simultaneously from the contrast-weighted images. Six-fold cross-validation was performed to compare the network outputs with the MR Multitasking references.
RESULTS: The deep-learning T1 /T2 maps were comparable with the references, and brain tissue structures and image contrasts were well preserved. A peak signal-to-noise ratio >32 dB and a structural similarity index >0.97 were achieved for both parameter maps. Calculated on brain parenchyma (excluding CSF), the mean absolute errors (and mean percentage errors) for T1 and T2 maps were 52.7 ms (5.1%) and 5.4 ms (7.1%), respectively. ROI measurements on four tissue compartments (cortical gray matter, white matter, putamen, and thalamus) showed that T1 and T2 values provided by the network outputs were in agreement with the MR Multitasking reference maps. The mean differences were smaller than ± 1%, and limits of agreement were within ± 5% for T1 and within ± 10% for T2 after taking the mean differences into account.
CONCLUSION: A deep-learning-based technique was developed to estimate T1 and T2 maps from conventional contrast-weighted images in the brain, enabling simultaneous qualitative and quantitative MRI without modifying clinical protocols.
© 2021 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  brain; deep learning; magnetic resonance imaging (MRI); multiparametric mapping; quantitative imaging

Mesh:

Year:  2021        PMID: 34374468      PMCID: PMC8616775          DOI: 10.1002/mrm.28962

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


  17 in total

1.  NMR relaxation times in the human brain at 3.0 tesla.

Authors:  J P Wansapura; S K Holland; R S Dunn; W S Ball
Journal:  J Magn Reson Imaging       Date:  1999-04       Impact factor: 4.813

2.  Quantitative MRI for Analysis of Active Multiple Sclerosis Lesions without Gadolinium-Based Contrast Agent.

Authors:  I Blystad; I Håkansson; A Tisell; J Ernerudh; Ö Smedby; P Lundberg; E-M Larsson
Journal:  AJNR Am J Neuroradiol       Date:  2015-10-15       Impact factor: 3.825

3.  Multi-parametric quantitative MRI of normal appearing white matter in multiple sclerosis, and the effect of disease activity on T2.

Authors:  Sarah C Reitz; Stephanie-Michelle Hof; Vinzenz Fleischer; Alla Brodski; Adriane Gröger; René-Maxime Gracien; Amgad Droby; Helmuth Steinmetz; Ulf Ziemann; Frauke Zipp; Ralf Deichmann; Johannes C Klein
Journal:  Brain Imaging Behav       Date:  2017-06       Impact factor: 3.978

4.  Quantitative mapping of T1 and T2* discloses nigral and brainstem pathology in early Parkinson's disease.

Authors:  Simon Baudrexel; Lucas Nürnberger; Udo Rüb; Carola Seifried; Johannes C Klein; Thomas Deller; Helmuth Steinmetz; Ralf Deichmann; Rüdiger Hilker
Journal:  Neuroimage       Date:  2010-03-06       Impact factor: 6.556

5.  Changes and variability of proton density and T1 relaxation times in early multiple sclerosis: MRI markers of neuronal damage in the cerebral cortex.

Authors:  René-Maxime Gracien; Sarah C Reitz; Stephanie Michelle Hof; Vinzenz Fleischer; Hilga Zimmermann; Amgad Droby; Helmuth Steinmetz; Frauke Zipp; Ralf Deichmann; Johannes C Klein
Journal:  Eur Radiol       Date:  2015-10-22       Impact factor: 5.315

6.  Quantitative T1 and T2 mapping in recurrent glioblastomas under bevacizumab: earlier detection of tumor progression compared to conventional MRI.

Authors:  Stephanie Lescher; Alina Jurcoane; Andreas Veit; Oliver Bähr; Ralf Deichmann; Elke Hattingen
Journal:  Neuroradiology       Date:  2014-10-07       Impact factor: 2.804

Review 7.  Fast robust automated brain extraction.

Authors:  Stephen M Smith
Journal:  Hum Brain Mapp       Date:  2002-11       Impact factor: 5.038

8.  Magnetic resonance multitasking for motion-resolved quantitative cardiovascular imaging.

Authors:  Anthony G Christodoulou; Jaime L Shaw; Christopher Nguyen; Qi Yang; Yibin Xie; Nan Wang; Debiao Li
Journal:  Nat Biomed Eng       Date:  2018-04-09       Impact factor: 25.671

9.  Three-dimensional whole-brain simultaneous T1, T2, and T1ρ quantification using MR Multitasking: Method and initial clinical experience in tissue characterization of multiple sclerosis.

Authors:  Sen Ma; Nan Wang; Zhaoyang Fan; Marwa Kaisey; Nancy L Sicotte; Anthony G Christodoulou; Debiao Li
Journal:  Magn Reson Med       Date:  2020-10-26       Impact factor: 4.668

10.  Magnetic resonance fingerprinting.

Authors:  Dan Ma; Vikas Gulani; Nicole Seiberlich; Kecheng Liu; Jeffrey L Sunshine; Jeffrey L Duerk; Mark A Griswold
Journal:  Nature       Date:  2013-03-14       Impact factor: 49.962

View more
  1 in total

1.  Three-dimensional simultaneous brain mapping of T1, T2, T2 and magnetic susceptibility with MR Multitasking.

Authors:  Tianle Cao; Sen Ma; Nan Wang; Sara Gharabaghi; Yibin Xie; Zhaoyang Fan; Elliot Hogg; Chaowei Wu; Fei Han; Michele Tagliati; E Mark Haacke; Anthony G Christodoulou; Debiao Li
Journal:  Magn Reson Med       Date:  2021-10-27       Impact factor: 3.737

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.