Beyond Conventional Parametric Modeling: Data-Driven Framework for Estimation and Prediction of Time Activity Curves in Dynamic PET Imaging
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914817885863936 |
|---|---|
| author | Zakariaei, Niloufar Rahmim, Arman Haber, Eldad |
| author_facet | Zakariaei, Niloufar Rahmim, Arman Haber, Eldad |
| contents | Dynamic Positron Emission Tomography (dPET) imaging and Time-Activity Curve (TAC) analyses are essential for understanding and quantifying the biodistribution of radiopharmaceuticals over time and space. Traditional compartmental modeling, while foundational, commonly struggles to fully capture the complexities of biological systems, including non-linear dynamics and variability. This study introduces an innovative data-driven neural network-based framework, inspired by Reaction Diffusion systems, designed to address these limitations. Our approach, which adaptively fits TACs from dPET, enables the direct calibration of diffusion coefficients and reaction terms from observed data, offering significant improvements in predictive accuracy and robustness over traditional methods, especially in complex biological scenarios. By more accurately modeling the spatio-temporal dynamics of radiopharmaceuticals, our method advances modeling of pharmacokinetic and pharmacodynamic processes, enabling new possibilities in quantitative nuclear medicine. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_21021 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beyond Conventional Parametric Modeling: Data-Driven Framework for Estimation and Prediction of Time Activity Curves in Dynamic PET Imaging Zakariaei, Niloufar Rahmim, Arman Haber, Eldad Machine Learning Image and Video Processing Dynamical Systems Dynamic Positron Emission Tomography (dPET) imaging and Time-Activity Curve (TAC) analyses are essential for understanding and quantifying the biodistribution of radiopharmaceuticals over time and space. Traditional compartmental modeling, while foundational, commonly struggles to fully capture the complexities of biological systems, including non-linear dynamics and variability. This study introduces an innovative data-driven neural network-based framework, inspired by Reaction Diffusion systems, designed to address these limitations. Our approach, which adaptively fits TACs from dPET, enables the direct calibration of diffusion coefficients and reaction terms from observed data, offering significant improvements in predictive accuracy and robustness over traditional methods, especially in complex biological scenarios. By more accurately modeling the spatio-temporal dynamics of radiopharmaceuticals, our method advances modeling of pharmacokinetic and pharmacodynamic processes, enabling new possibilities in quantitative nuclear medicine. |
| title | Beyond Conventional Parametric Modeling: Data-Driven Framework for Estimation and Prediction of Time Activity Curves in Dynamic PET Imaging |
| topic | Machine Learning Image and Video Processing Dynamical Systems |
| url | https://arxiv.org/abs/2405.21021 |