AUTHOR=Qureshi Shahzad Ahmad , Rehman Aziz Ul , Mir Adil Aslam , Rafique Muhammad , Muhammad Wazir 

TITLE=Simulated Annealing-Based Image Reconstruction for Patients With COVID-19 as a Model for Ultralow-Dose Computed Tomography

JOURNAL=Frontiers in Physiology

VOLUME=Volume 12 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2021.737233

DOI=10.3389/fphys.2021.737233

ISSN=1664-042X

ABSTRACT=The proposed algorithm of inverse problem of computed tomography (CT), using limited views, is based on stochastic techniques, namely simulated annealing (SA). The selection of an optimal cost function for SA-based image reconstruction is of prime importance. It can reduce annealing time, as well as X-rays dose rate accompanying better image quality. In this paper, effectiveness of various cost functions namely (universal image quality index (UIQI), root-mean-squared error (RMSE), structural similarity index measure (SSIM), mean absolute error (MAE), relative squared error (RSE), relative absolute error (RAE) and root-mean-squared logarithmic error (RMSLE)) have been critically analysed and evaluated for ultralow dose X-ray computed tomography (CT) of COVID-19 patients. For sensitivity analysis of this ill-posed problem, the stochastically estimated images of lung phantom have been reconstructed. The cost function analysis in terms of computational and spatial complexity has been performed using image quality measures, namely: peak signal-to-noise ratio (PSNR) and Euclidean error (EuE). It has been generalized for cost functions that RMSLE exhibits PSNR of 24.27±3.10 dB and 24.62 ±1.15 dB for 8 × 8 and 16 × 16 lung phantoms respectively, and it has been applied for actual CT based image reconstruction of COVID-19 patients. We successfully reconstructed COVID-19 patients’ chest CT images by using RMSLE with eighteen projections, a 10-fold reduction in radiation dose exposure. This approach will be suitable for accurate diagnosis of COVID-19 patients having less immunity and sensitive to radiation dose.