Non-invasive arterial input function estimation using an MRA atlas and machine learning.
Authors
Affiliations (7)
Affiliations (7)
- Centre for Advanced Imaging, University of Queensland, Brisbane, Australia.
- ARC Training Centre for Innovation in Biomedical Imaging Technology, University of Queensland, Brisbane, Australia.
- Siemens Healthcare Pty Ltd, Melbourne, Australia.
- Department of Nuclear Medicine, Bern University Hospital, Inselspital, University of Bern, Freiburgstrasse 18, Bern, 3010, Switzerland.
- Advanced Clinical Imaging Technology, Siemens Healthcare AG, Lausanne, Switzerland.
- Centre for Advanced Imaging, University of Queensland, Brisbane, Australia. [email protected].
- ARC Training Centre for Innovation in Biomedical Imaging Technology, University of Queensland, Brisbane, Australia. [email protected].
Abstract
Quantifying biological parameters of interest through dynamic positron emission tomography (PET) requires an arterial input function (AIF) conventionally obtained from arterial blood samples. The AIF can also be non-invasively estimated from blood pools in PET images, often identified using co-registered MRI images. Deploying methods without blood sampling or the use of MRI generally requires total body PET systems with a long axial field-of-view (LAFOV) that includes a large cardiovascular blood pool. However, the number of such systems in clinical use is currently much smaller than that of short axial field-of-view (SAFOV) scanners. We propose a data-driven approach for AIF estimation for SAFOV PET scanners, which is non-invasive and does not require MRI or blood sampling using brain PET scans. The proposed method was validated using dynamic <sup>18</sup>F-fluorodeoxyglucose [<sup>18</sup>F]FDG total body PET data from 10 subjects. A variational inference-based machine learning approach was employed to correct for peak activity. The prior was estimated using a probabilistic vascular MRI atlas, registered to each subject's PET image to identify cerebral arteries in the brain. The estimated AIF using brain PET images (IDIF-Brain) was compared to that obtained using data from the descending aorta of the heart (IDIF-DA). Kinetic rate constants (K<sub>1</sub>, k<sub>2</sub>, k<sub>3</sub>) and net radiotracer influx (K<sub>i</sub>) for both cases were computed and compared. Qualitatively, the shape of IDIF-Brain matched that of IDIF-DA, capturing information on both the peak and tail of the AIF. The area under the curve (AUC) of IDIF-Brain and IDIF-DA were similar, with an average relative error of 9%. The mean Pearson correlations between kinetic parameters (K<sub>1</sub>, k<sub>2</sub>, k<sub>3</sub>) estimated with IDIF-DA and IDIF-Brain for each voxel were between 0.92 and 0.99 in all subjects, and for K<sub>i</sub>, it was above 0.97. This study introduces a new approach for AIF estimation in dynamic PET using brain PET images, a probabilistic vascular atlas, and machine learning techniques. The findings demonstrate the feasibility of non-invasive and subject-specific AIF estimation for SAFOV scanners.