Build-A-FLAIR: Synthetic T2-FLAIR Contrast Generation through Physics Informed Deep Learning
Authors:
- Andrew S. NenckaANAndrew S. Nencka
- Andrew KleinAKAndrew Klein
- Kevin M. KochKKKevin M. Koch
- Sean D. McGarrySMSean D. McGarry
- Peter S. LaViolettePLPeter S. LaViolette
- Eric S. PaulsonEPEric S. Paulson
- Nikolai J. MickeviciusNMNikolai J. Mickevicius
- L. Tugan MuftulerLML. Tugan Muftuler
- Michael A. McCreaMMMichael A. McCrea
Preprint
Abstract
Purpose: Magnetic resonance imaging (MRI) exams include multiple series with varying contrast and redundant information. For instance, T2-FLAIR contrast is based upon tissue T2 decay and the presence of water, also present in T2- and diffusion-weighted contrasts. T2-FLAIR contrast can be hypothetically modeled through deep learning models trained with diffusion- and T2-weighted acquisitions. Methods: Diffusion-, T2-, T2-FLAIR-, and T1-weighted brain images were acquired in 15 individuals. A convolutional neural network was developed to generate a T2-FLAIR image from other contrasts. Two datasets were withheld from training for validation. Results: Inputs with physical relationships to T2-FLAIR contrast most significantly impacted performance. The best model yielded results similar to acquired T2-FLAIR images, with a structural similarity index of 0.909, and reproduced pathology excluded from training. Synthetic images qualitatively exhibited lower noise and increased smoothness compared to acquired images. Conclusion: This suggests that with optimal inputs, deep learning based contrast generation performs well with creating synthetic T2-FLAIR images. Feature engineering on neural network inputs, based upon the physical basis of contrast, impacts the generation of synthetic contrast images. A larger, prospective clinical study is needed.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Modeling the Structure of Acute Sport-Related Concussion Symptoms: A Bifactor ApproachJournal of the International Neuropsychological Society, 2018
- Image reconstruction by domain-transform manifold learningNature, 2018
- The first step for neuroimaging data analysis: DICOM to NIfTI conversionJournal of Neuroscience Methods, 2016
- Multiband multislice GE‐EPI at 7 tesla, with 16‐fold acceleration using partial parallel imaging with application to high spatial and temporal whole‐brain fMRIMagnetic Resonance in Medicine, 2010
- Rapid magnetic resonance quantification on the brain: Optimization for clinical usageMagnetic Resonance in Medicine, 2008
- Sparse MRI: The application of compressed sensing for rapid MR imagingMagnetic Resonance in Medicine, 2007
- Handbook of MRI Pulse Sequences2004
- Generalized autocalibrating partially parallel acquisitions (GRAPPA)Magnetic Resonance in Medicine, 2002
- ADC mapping of the human optic nerve: Increased resolution, coverage, and reliability with CSF‐suppressed ZOOM‐EPIMagnetic Resonance in Medicine, 2001
- A global optimisation method for robust affine registration of brain imagesMedical Image Analysis, 2001