Advertisement

Short Acquisition Time PET/MR Pharmacokinetic Modelling Using CNNs

  • Catherine J. Scott
  • Jieqing Jiao
  • M. Jorge Cardoso
  • Kerstin Kläser
  • Andrew Melbourne
  • Pawel J. Markiewicz
  • Jonathan M. Schott
  • Brian F. Hutton
  • Sébastien Ourselin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11070)

Abstract

Standard quantification of Positron Emission Tomography (PET) data requires a long acquisition time to enable pharmacokinetic (PK) model fitting, however blood flow information from Arterial Spin Labelling (ASL) Magnetic Resonance Imaging (MRI) can be combined with simultaneous dynamic PET data to reduce the acquisition time. Due the difficulty of fitting a PK model to noisy PET data with limited time points, such ‘fixed-\(R_1\)’ techniques are constrained to a 30 min minimum acquisition, which is intolerable for many patients. In this work we apply a deep convolutional neural network (CNN) approach to combine the PET and MRI data. This permits shorter acquisition times as it avoids the noise sensitive voxelwise PK modelling and facilitates the full modelling of the relationship between blood flow and the dynamic PET data. This method is compared to three fixed-\(R_1\) PK methods, and the clinically used standardised uptake value ratio (SUVR), using 60 min dynamic PET PK modelling as the gold standard. Testing on 11 subjects participating in a study of pre-clinical Alzheimer’s Disease showed that, for 30 min acquisitions, all methods which combine the PET and MRI data have comparable performance, however at shorter acquisition times the CNN approach has a significantly lower mean square error (MSE) compared to fixed-\(R_1\) PK modelling (\(p=0.001\)). For both acquisition windows, SUVR had a significantly higher MSE than the CNN method (\(p\le 0.003\)). This demonstrates that combining simultaneous PET and MRI data using a CNN can result in robust PET quantification within a scan time which is tolerable to patients with dementia.

Notes

Acknowledgements

This work was supported by the EPSRC UCL Centre for Doctoral Training in Medical Imaging (EP/L016478/1), UCL Leonard Wolfson Experimental Neurology Centre (PR/ylr/18575), MRC (MR/J01107X/1), EPSRC (NS/A000027/1), NIHR UCLH Biomedical Research Centre (inc. High Impact Initiative, BW.mn.BRC10269). Insight 1946 receives funding from Alzheimer’s Research UK (ARUKPG2014-1946, ARUKPG2014-1946), MRC Dementia Platform UK (CSUB19166), The Wolfson Foundation, and Brain Research Trust. The Florbetapir tracer was kindly supplied by Avid Radiopharmaceuticals, a wholly owned subsidiary of Eli Lilly. We are grateful to the Insight 46 participants for their involvement in this study and to K. Erlandsson for his advice.

References

  1. 1.
    Scott, C.J., et al.: ASL-incorporated pharmacokinetic modelling of PET data with reduced acquisition time: application to amyloid imaging. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9902, pp. 406–413. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46726-9_47CrossRefGoogle Scholar
  2. 2.
    van Berckel, B.N.M., Ossenkoppele, R., Tolboom, N., et al.: Longitudinal amyloid imaging using 11C-PiB: methodologic considerations. J. Cereb. Blood Flow Metab. 54(9), 1570–6 (2013)Google Scholar
  3. 3.
    Wu, Y., Carson, R.E.: Noise reduction in the simplified reference tissue model for neuroreceptor functional imaging. J. Cereb. Blood Flow Metab. 22(12), 1440–1452 (2002)CrossRefGoogle Scholar
  4. 4.
    Gibson, E., Li, W., Sudre, C., et al.: Niftynet: a deep-learning platform for medical imaging. arXiv preprint arXiv:1709.03485 (2017)
  5. 5.
    Li, W., Wang, G., Fidon, L., et al.: On the compactness, efficiency, and representation of 3D convolutional networks: brain parcellation as a pretext task. In: Information Processing in Medical Imaging (2017)Google Scholar
  6. 6.
    Gunn, R.N., Lammertsma, A.A., Hume, S.P., et al.: Parametric imaging of ligand-receptor binding in PET using a simplified reference region model. NeuroImage 6(4), 279–287 (1997)CrossRefGoogle Scholar
  7. 7.
    Scott, C., et al.: Short acquisition time PET quantification using MRI-based pharmacokinetic parameter synthesis. In: Descoteaux, M., et al. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 737–744. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66185-8_83CrossRefGoogle Scholar
  8. 8.
    Markiewicz, P.J., Ehrhardt, M.J., Erlandsson, K., et al.: NiftyPET: a High-throughput Software Platform for High Quantitative Accuracy and Precision PET Imaging and Analysis. Neuroinformatics 16(1), 95–115 (2017)CrossRefGoogle Scholar
  9. 9.
    Melbourne, A., Toussaint, N., Owen, D., et al.: Niftyfit: a software package for multi-parametric model-fitting of 4D magnetic resonance imaging data. Neuroinformatics 14(3), 319–337 (2016)CrossRefGoogle Scholar
  10. 10.
    Lane, C.A., Parker, T.D., Cash, D.M., et al.: Study protocol: Insight 46 - a neuroscience sub-study of the MRC National Survey of Health and Development. BMC Neurol. 17(1), 75 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Catherine J. Scott
    • 1
  • Jieqing Jiao
    • 1
  • M. Jorge Cardoso
    • 1
    • 2
  • Kerstin Kläser
    • 1
  • Andrew Melbourne
    • 2
    • 3
  • Pawel J. Markiewicz
    • 1
  • Jonathan M. Schott
    • 4
  • Brian F. Hutton
    • 5
  • Sébastien Ourselin
    • 2
  1. 1.Centre for Medical Image ComputingUniversity College LondonLondonUK
  2. 2.School of Biomedical Engineering and Imaging SciencesKing’s College LondonLondonUK
  3. 3.Department of Medical Physics and Biomedical EngineeringUniversity College LondonLondonUK
  4. 4.Dementia Research Centre, Institute of NeurologyUniversity College LondonLondonUK
  5. 5.Institute of Nuclear MedicineUniversity College LondonLondonUK

Personalised recommendations