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

BMC Medical Imaging

Jianfeng He¹  Yongjin Li¹  Tao Wang¹  Yinglei Deng²  Shaobo Wang² 

[1] Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Yunnan Key Laboratory of Artificial Intelligence, 650500, Kunming, Yunnan, China;PET/CT Center, Affiliated Hospital of Kunming University of Science and Technology, First People’s Hospital of Yunnan, 650031, Kunming, China;

关键词: Kinetic models;    PET/CT;    Hepatocellular carcinoma;    Gravitational search algorithm;   

DOI  :  10.1186/s12880-022-00742-4

来源: Springer

【 摘 要 】

BackgroundKinetic parameters estimated with dynamic 18F-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.MethodsFive-minute dynamic PET/CT data of 20 HCCs were prospectively enrolled, and the kinetic parameters k1 ~ k4 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.ResultsThe results showed that there were significant differences between the HCCs and background liver tissues for k1, k4 and the HPI of NLLS; k1, k3, k4 and the HPI of GSA; and k1, k2, k3, k4 and the HPI of DCGSA. DCGSA had a higher diagnostic performance for k3 than NLLS and GSA.ConclusionsGSA enables accurate estimation of the kinetic parameters of dynamic PET/CT in the diagnosis of HCC, and DCGSA can enhance the diagnostic performance.

【 授权许可】

CC BY