Dynamic chaotic gravitational search algorithm-based kinetic parameter estimation of hepatocellular carcinoma on (18)F-FDG PET/CT

BACKGROUND: Kinetic parameters estimated with dynamic (18)F-FDG PET/CT can help to characterize hepatocellular carcinoma (HCC). We aim to evaluate the feasibility of the gravitational search algorithm (GSA) for kinetic parameter estimation and to propose a dynamic chaotic gravitational search algorithm (DCGSA) to enhance parameter estimation. METHODS: Five-minute dynamic PET/CT data of 20 HCCs were prospectively enrolled, and the kinetic parameters k(1) ~ k(4) and the hepatic arterial perfusion index (HPI) were estimated with a dual-input three-compartment model based on nonlinear least squares (NLLS), GSA and DCGSA. RESULTS: The results showed that there were significant differences between the HCCs and background liver tissues for k(1), k(4) and the HPI of NLLS; k(1), k(3), k(4) and the HPI of GSA; and k(1), k(2), k(3), k(4) and the HPI of DCGSA. DCGSA had a higher diagnostic performance for k(3) than NLLS and GSA. CONCLUSIONS: GSA enables accurate estimation of the kinetic parameters of dynamic PET/CT in the diagnosis of HCC, and DCGSA can enhance the diagnostic performance.