Short Acquisition Time PET/MR Pharmacokinetic Modelling Using CNNs
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.
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.
- 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.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
- 4.Gibson, E., Li, W., Sudre, C., et al.: Niftynet: a deep-learning platform for medical imaging. arXiv preprint arXiv:1709.03485 (2017)
- 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