LOW-DOSE CT IN LUNG PATHOLOGIES RELATED TO RHEUMATOID ARTHRITIS: COMPARISON OF DEEP LEARNING-BASED NOISE REDUCTION ALGORITHM AND ITERATIVE RECONSTRUCTION ALGORITHM
DOI:
https://doi.org/10.66288/actamedi.2026.87Keywords:
Low-dose chest CT, Image quality evaluation, Deep learning-based noise reduction, Radiation doseAbstract
AIM: Imaging techniques play a critical role in the evaluation of lung pathologies in patients diagnosed with RA. However, conventional CT scans may require high radiation doses, which can cause undesirable effects, especially in RA patients requiring long-term follow-up. Therefore, the use of low-dose CT scans has become increasingly important. The aim of this study is to compare the effectiveness of a deep learning-based noise reduction algorithm and an iterative reconstruction algorithm in the evaluation of lung pathologies observed in patients diagnosed with RA using low-dose CT.
METHODOLOGY: Standard dose CT scans and low dose CT scans ( Precise 30 mAs and 45 mAs) obtained with deep learning-based noise reduction method of patients followed up with the diagnosis of rheumatoid arthritis were evaluated in terms of visual quality, image noise and contrast-to-noise ratio.
RESULTS: In the visual assessment scoring, standard dose imaging and Precise 45 mAs images were found to be statistically compatible, but there was a discrepancy in the 30 mAs images. In the image noise evaluation, image noise was found to be statistically significantly higher in both the mediastinum and parenchymal windows in 30 mAs images (p<0.001). Post-hoc evaluations of CNR revealed that the CNR values of standard and Precise 45 mAs imaging in the mediastinal window were similar, while Precise 30 mAs imaging had a statistically significantly lower CNR value (p<0.001). Significant differences were found in total DLP values among all three imaging protocols (p<0.001).
CONCLUSION: In evaluating the image quality obtained with different dose protocols in low-dose thoracic CT scans of patients diagnosed with RA, it was observed that the deep learning-based reconstruction algorithm provided diagnostically reliable results, especially at the 45 mAs level.
References
1.Demirel A, Kırnap M. Romatoid Artrit Tedvisinde Geleneksel ve Güncel Yaklaşımlar. Sağlık Bilimleri Dergisi. 2010;19(1):74-84.
2.Karazincir S, Akoğlu S, Güler H, Balci A, Babayiğit C, Eğilmez E. The evaluation of early pulmonary involvement with high resolution computerized tomography in asymptomatic and non-smoker patients with rheumatoid arthritis. Tuberkuloz ve Toraks. 2009;57(1):14-21.
3.Kelly BS, Judge C, Bollard SM, Clifford SM, Healy GM, Aziz A, et al. Radiology artificial intelligence: a systematic review and evaluation of methods (RAISE). European radiology. 2022;32(11):7998-8007. DOI: https://doi.org/10.1007/s00330-022-08784-6
4.Ozaki S, Haga A, Chao E, Maurer C, Nawa K, Ohta T, et al. Fast statistical iterative reconstruction for mega-voltage computed tomography. The Journal of Medical Investigation. 2020;67(1.2):30-9. DOI: https://doi.org/10.2152/jmi.67.30
5.Hackner K, Hütter L, Flick H, Grohs M, Kastrati K, Kiener H, et al. Screening for rheumatoid arthritis-associated interstitial lung disease-a Delphi-based consensus statement. Z Rheumatol. 2024;83(2):160-8. DOI: https://doi.org/10.1007/s00393-023-01464-w
6.Brenner DJ, Hall EJ. Computed tomography--an increasing source of radiation exposure. N Engl J Med. 2007;357(22):2277-84. DOI: https://doi.org/10.1056/NEJMra072149
7.Szczykutowicz TP, Toia GV, Dhanantwari A, Nett B. A review of deep learning CT reconstruction: concepts, limitations, and promise in clinical practice. Current Radiology Reports. 2022;10(9):101-15. DOI: https://doi.org/10.1007/s40134-022-00399-5
8.Choy S, Parhar D, Lian K, Schmiedeskamp H, Louis L, O'Connell T, et al. Comparison of image noise and image quality between full-dose abdominal computed tomography scans reconstructed with weighted filtered back projection and half-dose scans reconstructed with improved sinogram-affirmed iterative reconstruction (SAFIRE*). Abdom Radiol . 2019;44(1):355-61. DOI: https://doi.org/10.1007/s00261-018-1687-9
9.Lee SW, Kim Y, Shim SS, Lee JK, Lee SJ, Ryu YJ, et al. Image quality assessment of ultra low-dose chest CT using sinogram-affirmed iterative reconstruction. Eur Radiol. 2014;24(4):817-26. DOI: https://doi.org/10.1007/s00330-013-3090-9
10.Ding L, Chen M, Li X, Wu Y, Li J, Deng S, et al. Ultra-low dose dual-layer detector spectral CT for pulmonary nodule screening: image quality and diagnostic performance. Insights Imaging. 2025;16(1):11 DOI: https://doi.org/10.1186/s13244-024-01888-1
11.Vardhanabhuti V, Pang CL, Tenant S, Taylor J, Hyde C, Roobottom C. Prospective intra-individual comparison of standard dose versus reduced-dose thoracic CT using hybrid and pure iterative reconstruction in a follow-up cohort of pulmonary nodules-Effect of detectability of pulmonary nodules with lowering dose based on nodule size, type and body mass index. Eur J Radiol. 2017;91:130-41. DOI: https://doi.org/10.1016/j.ejrad.2017.04.006
12.Power SP, Moloney F, Twomey M, James K, O'Connor OJ, Maher MM. Computed tomography and patient risk: Facts, perceptions and uncertainties. World J Radiol. 2016;8(12):902-15. DOI: https://doi.org/10.4329/wjr.v8.i12.902
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Aybuke Uçar, Inan Korkmaz
This work is licensed under a Creative Commons Attribution 4.0 International License.
