Related Experiment Video
Updated: Jul 15, 2026
PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
Published on: December 28, 2017
Optimization of a Q.Clear PET image reconstruction based on bayesian optimization in oncology and neurology
Qariemah Azahar1, Hazlin Hashim1,2, Khadijah Abdul Hamid1,2
1Department of Biomedical Imaging, Pusat Kanser Tun Abdullah Ahmad Badawi, Universiti Sains Malaysia, 13200, Kepala Batas, Penang, Malaysia.
Abstract:
Bayesian Penalized Likelihood (BPL) reconstruction can improve image quality and quantitative accuracy in PET/CT imaging. This study aimed to determine the optimal Beta (β)-factor in Q.Clear reconstruction using Bayesian Optimization (BO) through phantoms and clinical evaluation. NEMA IQ and Hoffman Brain phantoms, along with clinical PET/CT images, were analyzed. Phantom images were reconstructed using β-factors (50-1000) across different acquisition times. Recovery coefficient (RC%) and contrast-to-noise ratio (CNR) were calculated. Clinical evaluation included one neurology and one oncology case as verification data, reconstructed using OSEM and Q.Clear at β-factors (100-1000), with full and reduced reconstruction times (neurology: 8 and 2 min; oncology: 15 and 7 min), respectively. Visual assessment was independently performed by two nuclear medicine physicians, and inter-rater agreement was analyzed using Krippendorff's alpha. In the NEMA IQ phantom, increasing β-factor resulted in decreased RC% but increased CNR. In the Hoffman Brain phantom, cortical regions showed stable RC% from mid to high β-factors, whereas subcortical regions were more sensitive, showing reduced RC%. CNR improved with higher β-factors and longer acquisition times. BO analysis indicates that smaller spheres achieved optimal performance at lower β-factors and longer acquisition times, while larger spheres tolerated higher β-factors (600-800). Optimal β-factors for cortical and subcortical brain regions were (400-600) and (100-300), respectively. Clinically, the highest scores were observed for β-factors (300-1000) in oncology, and (500-900) in neurology. Higher β-factors improved RC% and CNR stability in phantom studies. BO identified (500-900) as the optimal β-factors, consistent with clinical findings demonstrating high visual scores and strong inter-rater agreement, supporting its reliability of BO-optimized β-factors for PET/CT reconstruction.
