Publications

BibTex format

@article{Ferrante:2024:10.1016/j.cmpb.2024.108375,
author = {Ferrante, M and Inglese, M and Brusaferri, L and Whitehead, AC and Maccioni, L and Turkheimer, FE and Nettis, MA and Mondelli, V and Howes, O and Loggia, ML and Veronese, M and Toschi, N},
doi = {10.1016/j.cmpb.2024.108375},
journal = {Comput Methods Programs Biomed},
title = {Physically informed deep neural networks for metabolite-corrected plasma input function estimation in dynamic PET imaging.},
url = {http://dx.doi.org/10.1016/j.cmpb.2024.108375},
volume = {256},
year = {2024}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - 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 [11C]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.
AU  - Ferrante,M
AU  - Inglese,M
AU  - Brusaferri,L
AU  - Whitehead,AC
AU  - Maccioni,L
AU  - Turkheimer,FE
AU  - Nettis,MA
AU  - Mondelli,V
AU  - Howes,O
AU  - Loggia,ML
AU  - Veronese,M
AU  - Toschi,N
DO  - 10.1016/j.cmpb.2024.108375
PY  - 2024///
TI  - Physically informed deep neural networks for metabolite-corrected plasma input function estimation in dynamic PET imaging.
T2  - Comput Methods Programs Biomed
UR  - http://dx.doi.org/10.1016/j.cmpb.2024.108375
UR  - https://www.ncbi.nlm.nih.gov/pubmed/39180914
VL  - 256
ER  -

Download

Publications

Citation

BibTex format

RIS format (EndNote, RefMan)

Contact