Ferrante, Matteo;
Inglese, Marianna;
Brusaferri, Ludovica;
Whitehead, Alexander C;
Maccioni, Lucia;
Turkheimer, Federico E;
Nettis, Maria A;
... Toschi, Nicola; + view all
(2024)
Physically informed deep neural networks for metabolite-corrected plasma input function estimation in dynamic PET imaging.
Computer Methods and Programs in Biomedicine
, 256
, Article 108375. 10.1016/j.cmpb.2024.108375.
Preview |
Text
Physically informed deep neural networks for metabolite-corrected plasma input function estimation in dynamic PET imaging.pdf - Published Version Download (1MB) | Preview |
Abstract
Introduction: We propose a novel approach for the non-invasive quantification of dynamic PET imaging data, focusing on the arterial input function (AIF) without the need for invasive arterial cannulation. // Methods: Our method utilizes a combination of three-dimensional depth-wise separable convolutional layers and a physically informed deep neural network to incorporatea priori knowledge about the AIF’s functional form and shape, enabling precise predictions of the concentrations of [11 C ]PBR28 in whole blood and the free tracer in metabolite-corrected plasma. // Results: We found a robust linear correlation between our model’s predicted AIF curves and those obtained through traditional, invasive measurements. We achieved an average cross-validated Pearson correlation of 0.86 for whole blood and 0.89 for parent plasma curves. Moreover, our method’s ability to estimate the volumes of distribution across several key brain regions – without significant differences between the use of predicted versus actual AIFs in a two-tissue compartmental model – successfully captures the intrinsic variability related to sex, the binding affinity of the translocator protein (18 kDa), and age. // Conclusions: These results not only validate our method’s accuracy and reliability but also establish a foundation for a streamlined, non-invasive approach to dynamic PET data quantification. By offering a precise and less invasive alternative to traditional quantification methods, our technique holds significant promise for expanding the applicability of PET imaging across a wider range of tracers, thereby enhancing its utility in both clinical research and diagnostic settings.
| Type: | Article |
|---|---|
| Title: | Physically informed deep neural networks for metabolite-corrected plasma input function estimation in dynamic PET imaging |
| Location: | Ireland |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1016/j.cmpb.2024.108375 |
| Publisher version: | https://doi.org/10.1016/j.cmpb.2024.108375 |
| Language: | English |
| Additional information: | Copyright © 2024 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
| Keywords: | Physics informed neural networks; PET; IDIF; AIF; Metabolic imaging; TSPO |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Chemical Engineering |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10206113 |
Archive Staff Only
 |
View Item |
