Synthetic 18F-FDG PET Image Generation Using a Combination of Biomathematical Modeling and Machine Learning

Abstract

No previous works have attempted to combine generative adversarial network (GAN) architectures and the biomathematical modeling of positron emission tomography (PET) radiotracer uptake in tumors to generate extra training samples. Here, we developed a novel computational model to produce synthetic 18F-fluorodeoxyglucose (18F-FDG) PET images of solid tumors in different stages of progression and angiogenesis. First, a comprehensive biomathematical model is employed for creating tumor-induced angiogenesis, intravascular and extravascular fluid flow, as well as modeling of the transport phenomena and reaction processes of 18F-FDG in a tumor microenvironment. Then, a deep convolutional GAN (DCGAN) model is employed for producing synthetic PET images using 170 input images of 18F-FDG uptake in each of 10 different tumor microvascular networks. The interstitial fluid parameters and spatiotemporal distribution of 18F-FDG uptake in tumor and healthy tissues have been compared against previously published numerical and experimental studies, indicating the accuracy of the model. The structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) of the generated PET sample and the experimental one are 0.72 and 28.53, respectively. Our results demonstrate that a combination of biomathematical modeling and GAN-based augmentation models provides a robust framework for the non-invasive and accurate generation of synthetic PET images of solid tumors in different stages.

Targeted Nano Sized Drug Delivery to Heterogeneous Solid Tumor Microvasculatures: Implications for Immunoliposomes Exhibiting Bystander Killing Effect

“…A detailed description of the mathematical modeling of tumor-induced angiogenesis and related parameter values are presented in the supplementary file and our previous work 28 .…”

“…The tumor and adjacent healthy tissues can be assumed to be a porous environment 28 . The interstitial fluid parameter is determined by coupling the conservation equations for momentum and mass.…”

“…The interstitial fluid parameter is determined by coupling the conservation equations for momentum and mass. The momentum conservation equation for incompressible and Newtonian fluid within a porous environment (by neglecting the friction within the fluid as well as the solid and fluid stages) is simplified to Darcy’s law at a steady-state phase 28 . Darcy equation, which describes the convective contribution of the interstitial fluid fields, is given as follows 28 : where is the interstitial fluid velocity (IFV), P i is the IFP, and k is the hydraulic conductivity of the interstitial fluid.…”

“…The momentum conservation equation for incompressible and Newtonian fluid within a porous environment (by neglecting the friction within the fluid as well as the solid and fluid stages) is simplified to Darcy’s law at a steady-state phase 28 . Darcy equation, which describes the convective contribution of the interstitial fluid fields, is given as follows 28 : where is the interstitial fluid velocity (IFV), P i is the IFP, and k is the hydraulic conductivity of the interstitial fluid.…”

Spatiotemporal multi-scale modeling of radiopharmaceutical distributions in vascularized solid tumors

“…This assumption appears unrealistic in light of recent discoveries about the pivotal role of the tumor micro-environment in treatment success and failure 13 , 14 . To address this unmet and critical need, the conventional temporal models (such as compartmental kinetic analysis based on ordinary differential equations (ODEs) 15 , 16 ) should be updated using spatiotemporal distribution models (SDMs) based on partial differential equations (PDEs)) 17 – 24 . This study aimed to model one of the microenvironment variables: neovasculature.…”