Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jan 14:12:737233.
doi: 10.3389/fphys.2021.737233. eCollection 2021.

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

Shahzad Ahmad Qureshi  1 , Aziz Ul Rehman  2 , Adil Aslam Mir  3   4 , Muhammad Rafique  5 , Wazir Muhammad  6
Affiliations

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

Shahzad Ahmad Qureshi et al. Front Physiol. .

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, and also X-ray 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), has been critically analyzed and evaluated for ultralow-dose X-ray CT of patients with COVID-19. 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), Euclidean error (EuE), and weighted peak signal-to-noise ratio (WPSNR). It has been generalized for cost functions that RMSLE exhibits WPSNR of 64.33 ± 3.98 dB and 63.41 ± 2.88 dB for 8 × 8 and 16 × 16 lung phantoms, respectively, and it has been applied for actual CT-based image reconstruction of patients with COVID-19. We successfully reconstructed chest CT images of patients with COVID-19 using RMSLE with eighteen projections, a 10-fold reduction in radiation dose exposure. This approach will be suitable for accurate diagnosis of patients with COVID-19 having less immunity and sensitive to radiation dose.

Keywords: COVID-19 patients; Radon transform; cost functions; inverse problem; simulated annealing; ultralow dose CT.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

FIGURE 1
FIGURE 1
Model depicting forward projection at an orthogonal distance t through the center of a hypothetical cross-section f(x,y) of lung rotated by θ in Cartesian coordinates (x,y).
FIGURE 2
FIGURE 2
Ultralow Dose CT-based image reconstruction of COVID-19 patient’s lungs using simulated annealing.
FIGURE 3
FIGURE 3
Pseudocode for the image reconstruction algorithm.
FIGURE 4
FIGURE 4
The 512 × 512 pixels lung phantom.
FIGURE 5
FIGURE 5
Comparison between 8 × 8 and 16 × 16-sized image reconstruction using simulated annealing for the lung phantom, by using original phantom image, and cost functions (UIQI, RMSE, SSIM, MAE, RSE, RAE, and RMSLE) (p = 18, T0 = 0.1, TN = ×10−6, N = 8×105, temperature slab thickness set to 1000, and temperature profile as given by Eq. 4).
FIGURE 6
FIGURE 6
Convergence trends as normalized error variation against annealing time for (A) 8 × 8, and (B) 16 × 16 (N = 8×105) lung phantom reconstruction using fan beam projections.
FIGURE 7
FIGURE 7
8 × 8, 16 × 16, and 64 × 64-sized COVID-19 reconstructed images using simulated annealing with RMSLE as cost function (p = 18, T0 = 0.1, TN = 1 × 10−6, N = 2 × 105, temperature slab thickness set to 1000, and temperature profile as given by Eq. 4).
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Agostini A., Floridi C., Borgheresi A., Badaloni M., Pirani P. E., Terilli F., et al. (2020). Proposal of a low-dose, long-pitch, dual-source chest CT protocol on third-generation dual-source CT using a tin filter for spectral shaping at 100 kVp for coronavirus disease 2019 (COVID-19) patients: a feasibility study. Radiol. Med. 125 365–373. 10.1007/s11547-020-01179-x - DOI - PMC - PubMed
    1. Ai T., Yang Z., Hou H., Zhan C., Chen C., Lv W., et al. (2020). Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: a report of 1014 cases. Radiology 296 E32–E40. 10.1148/radiol.2020200642 - DOI - PMC - PubMed
    1. Andersen A. H. (1989). Algebraic reconstruction in CT from limited views. IEEE Trans. Med. Imaging 8 50–55. 10.1109/42.20361 - DOI - PubMed
    1. Arnold B. F., Stahlecker P. (2002). Linear regression analysis using the relative squared error. Linear Algebra Appl. 354 3–20.
    1. Bhatia M., Karl W. C., Willsky A. S. (1996). A wavelet-based method for multiscale tomographic reconstruction. IEEE Trans. Med. Imaging 15 92–101. 10.1109/42.481444 - DOI - PubMed