Physically informed deep neural networks for metabolite-corrected plasma input function estimation in dynamic PET imaging

Comput Methods Programs Biomed. 2024 Nov:256:108375. doi: 10.1016/j.cmpb.2024.108375. Epub 2024 Aug 20.

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 [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.

Keywords: AIF; IDIF; Metabolic imaging; PET; Physics informed neural networks; TSPO.

MeSH terms

  • Adult
  • Algorithms
  • Brain* / diagnostic imaging
  • Brain* / metabolism
  • Female
  • Humans
  • Image Processing, Computer-Assisted / methods
  • Male
  • Middle Aged
  • Neural Networks, Computer*
  • Positron-Emission Tomography* / methods
  • Pyridines
  • Receptors, GABA / metabolism
  • Reproducibility of Results

Substances

  • Pyridines
  • Receptors, GABA