Accelerating GluCEST imaging using deep learning for B0 correction
Yiran Li
Department of Electrical and Computer Engineering, Temple University, Philadelphia, Pennsylvania, USA
Search for more papers by this authorDanfeng Xie
Department of Electrical and Computer Engineering, Temple University, Philadelphia, Pennsylvania, USA
Search for more papers by this authorAbigail Cember
Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorRavi Prakash Reddy Nanga
Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorHanlu Yang
Department of Electrical and Computer Engineering, Temple University, Philadelphia, Pennsylvania, USA
Search for more papers by this authorDushyant Kumar
Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorHari Hariharan
Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorLi Bai
Department of Electrical and Computer Engineering, Temple University, Philadelphia, Pennsylvania, USA
Search for more papers by this authorJohn A. Detre
Department of Neurology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorRavinder Reddy
Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorCorresponding Author
Ze Wang
Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, Maryland, USA
Correspondence
Ze Wang, Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD 21201, USA.
Email: [email protected]
Twitter: @zewang79875503
Search for more papers by this authorYiran Li
Department of Electrical and Computer Engineering, Temple University, Philadelphia, Pennsylvania, USA
Search for more papers by this authorDanfeng Xie
Department of Electrical and Computer Engineering, Temple University, Philadelphia, Pennsylvania, USA
Search for more papers by this authorAbigail Cember
Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorRavi Prakash Reddy Nanga
Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorHanlu Yang
Department of Electrical and Computer Engineering, Temple University, Philadelphia, Pennsylvania, USA
Search for more papers by this authorDushyant Kumar
Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorHari Hariharan
Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorLi Bai
Department of Electrical and Computer Engineering, Temple University, Philadelphia, Pennsylvania, USA
Search for more papers by this authorJohn A. Detre
Department of Neurology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorRavinder Reddy
Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
Search for more papers by this authorCorresponding Author
Ze Wang
Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, Maryland, USA
Correspondence
Ze Wang, Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD 21201, USA.
Email: [email protected]
Twitter: @zewang79875503
Search for more papers by this authorAbstract
Purpose
Glutamate weighted Chemical Exchange Saturation Transfer (GluCEST) MRI is a noninvasive technique for mapping parenchymal glutamate in the brain. Because of the sensitivity to field (B0) inhomogeneity, the total acquisition time is prolonged due to the repeated image acquisitions at several saturation offset frequencies, which can cause practical issues such as increased sensitivity to patient motions. Because GluCEST signal is derived from the small z-spectrum difference, it often has a low signal-to-noise-ratio (SNR). We proposed a novel deep learning (DL)-based algorithm armed with wide activation neural network blocks to address both issues.
Methods
B0 correction based on reduced saturation offset acquisitions was performed for the positive and negative sides of the z-spectrum separately. For each side, a separate deep residual network was trained to learn the nonlinear mapping from few CEST-weighted images acquired at different ppm values to the one at 3 ppm (where GluCEST peaks) in the same side of the z-spectrum.
Results
All DL-based methods outperformed the “traditional” method visually and quantitatively. The wide activation blocks-based method showed the highest performance in terms of Structural Similarity Index (SSIM) and peak signal-to-noise ratio (PSNR), which were 0.84 and 25dB respectively. SNR increases in regions of interest were over 8dB.
Conclusion
We demonstrated that the new DL-based method can reduce the entire GluCEST imaging time by ˜50% and yield higher SNR than current state-of-the-art.
Supporting Information
| Filename | Description |
|---|---|
| mrm28289-sup-0001-Supinfo.docxWord document, 608.7 KB |
FIGURE S1 The prediction results of two testing subjects with low R square value were evaluated. The major image discrepancy across the reference and the DL methods came from the area marked by the red rectangles TABLE S1 The quantitative results of mean SSIM, PSNR, and CNR for different DL-based methods (A) and cross validation of three groups in terms of same performace indices TABLE S2 The post hoc tests of ANOVA test for SSIM (A), PSNR (B), and CNR (C) were calculated. Unet-5-pair has significant difference with WDSR-5/7-pair model in terms of SSIM TABLE S3 Voxelwise R2 value of each training subject TABLE S4 Voxelwise R2 value of each testing subject |
Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.
REFERENCES
- 1Forsén S, Hoffman RA. Study of moderately rapid chemical exchange reactions by means of nuclear magnetic double resonance. J Chem Phys. 1963; 39: 2892-2901.
- 2Ward KM, Aletras AH, Balaban RS. A new class of contrast agents for MRI based on proton chemical exchange dependent saturation transfer (CEST). J Magn Reson. 2000; 143: 79-87.
- 3Zhou J, Van Zijl PC. Chemical exchange saturation transfer imaging and spectroscopy. Prog Nucl Magn Reson Spectrosc. 2006; 48: 109-136.
- 4Cai K, Haris M, Singh A, et al. Magnetic resonance imaging of glutamate. Nat Med. 2012; 18: 302-306.
- 5Haris M, Nanga RPR, Singh A, et al. Exchange rates of creatine kinase metabolites: Feasibility of imaging creatine by chemical exchange saturation transfer MRI. NMR Biomed. 2012; 25: 1305-1309.
- 6Haris M, Cai K, Singh A, Hariharan H, Reddy R. In vivo mapping of brain myo-inositol. Neuroimage. 2011; 54: 2079-2085.
- 7DeBrosse C, Nanga RPR, Bagga P, et al. Lactate chemical exchange saturation transfer (LATEST) imaging in vivo: A biomarker for LDH activity. Sci Rep. 2016; 6: 19517.
- 8Saar G, Zhang B, Ling W, Regatte RR, Navon G, Jerschow A. Assessment of glycosaminoglycan concentration changes in the intervertebral disc via chemical exchange saturation transfer. NMR Biomed. 2012; 25: 255-261.
- 9Chan KWY, McMahon MT, Kato Y, et al. Natural D-glucose as a biodegradable MRI contrast agent for detecting cancer. Magn Reson Med. 2012; 68: 1764-1773.
- 10Henkelman RM, Stanisz GJ, Graham SJ. Magnetization transfer in MRI: A review. NMR Biomed. 2001; 14: 57-64.
- 11Davis KA, Nanga RPR, Das S, et al. Glutamate imaging (GluCEST) lateralizes epileptic foci in nonlesional temporal lobe epilepsy. Sci Transl Med. 2015; 7: 309ra161-309ra161.
- 12Roalf DR, Nanga RPR, Rupert PE, et al. Glutamate imaging (GluCEST) reveals lower brain GluCEST contrast in patients on the psychosis spectrum. Mol Psychiatry. 2017; 22: 1298.
- 13Neal A, Moffat BA, Stein JM, et al. Glutamate weighted imaging contrast in gliomas with 7 Tesla magnetic resonance imaging. Neuroimage Clin. 2019; 22: 101694.
- 14Haris M, Nath K, Cai K, et al. Imaging of glutamate neurotransmitter alterations in Alzheimer’s disease. NMR Biomed. 2013; 26: 386-391.
- 15Crescenzi R, DeBrosse C, Nanga RPR, et al. In vivo measurement of glutamate loss is associated with synapse loss in a mouse model of tauopathy. NeuroImage. 2014; 101: 185-192.
- 16Bagga P, Crescenzi R, Krishnamoorthy G, et al. Mapping the alterations in glutamate with Glu CEST MRI in a mouse model of dopamine deficiency. J Neurochem. 2016; 139: 432-439.
- 17Crescenzi R, DeBrosse C, Nanga RPR, et al. Longitudinal imaging reveals subhippocampal dynamics in glutamate levels associated with histopathologic events in a mouse model of tauopathy and healthy mice. Hippocampus. 2017; 27: 285-302.
- 18Bagga P, Pickup S, Crescenzi R, et al. In vivo GluCEST MRI: Reproducibility, background contribution and source of glutamate changes in the MPTP model of Parkinson’s disease. Sci Rep. 2018; 8: 2883.
- 19Nanga RPR, DeBrosse C, Kumar D, et al. Reproducibility of 2D GluCEST in healthy human volunteers at 7 T. Magn Reson Med. 2018; 80: 2033-2039.
- 20Zhou J, Blakeley JO, Hua J, et al. Practical data acquisition method for human brain tumor amide proton transfer (APT) imaging. Magn Reson Med. 2008; 60: 842-849.
- 21Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: F Pereira, CJC Burges, L Bottou, KQ Weinberger, eds. Advances in Neural Information Processing Systems. 2012; 1097-1105.
- 22Lin T-Y, Dollár P, Girshick R, He K, Hariharan B, Belongie S. Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017; 2117-2125.
- 23Young T, Hazarika D, Poria S, Cambria E. Recent trends in deep learning based natural language processing. IEEE Comput Intell Mag. 2018; 13: 55-75.
- 24Zhang Z, Liang X, Dong X, Xie Y, Cao G. A sparse-view CT reconstruction method based on combination of DenseNet and deconvolution. IEEE Trans Med Imaging. 2018; 37: 1407-1417.
- 25Xie D, Li Y, Yang H, et al. Denoising arterial spin labeling cerebral blood flow images using deep learning. Magn Reson Imaging. 2020; 68: 95-105.
- 26Ulas C, Tetteh G, Kaczmarz S, Preibisch C, Menze BH. DeepASL: Kinetic model incorporated loss for denoising arterial spin labeled MRI via deep Residual Learning. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. 2018; 30-38.
- 27Gong E, Pauly JM, Wintermark M, Zaharchuk G. Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI. J Magn Reson Imaging. 2018; 48: 330-340.
- 28Zaiss M, Deshmane A, Schuppert M, et al. DeepCEST: 9.4 T Chemical exchange saturation transfer MRI contrast predicted from 3 T data-a proof of concept study. arXiv Prepr. arXiv1808.10190. 2018.
- 29Yu J, Fan Y, Yang J, et al. Wide activation for efficient and accurate image super-resolution. arXiv Prepr. arXiv1808.08718. 2018.
- 30Kim M, Gillen J, Landman BA, Zhou J, Van Zijl PCM. Water saturation shift referencing (WASSR) for chemical exchange saturation transfer (CEST) experiments. Magn Reson Med. 2009; 61: 1441-1450.
- 31Atkins MS, Mackiewich BT. Fully automatic segmentation of the brain in MRI. IEEE Trans Med Imaging. 1998; 17: 98-107.
- 32Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. 2015; 234-241.
