Ultra-low-dose chest CT imaging of COVID-19 patients using a deep residual neural network.
Artificial intelligence
COVID-19
Deep learning
Tomography X-ray computed
Journal
European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774
Informations de publication
Date de publication:
Mar 2021
Mar 2021
Historique:
received:
09
06
2020
accepted:
21
08
2020
revised:
13
08
2020
pubmed:
4
9
2020
medline:
23
2
2021
entrez:
4
9
2020
Statut:
ppublish
Résumé
The current study aimed to design an ultra-low-dose CT examination protocol using a deep learning approach suitable for clinical diagnosis of COVID-19 patients. In this study, 800, 170, and 171 pairs of ultra-low-dose and full-dose CT images were used as input/output as training, test, and external validation set, respectively, to implement the full-dose prediction technique. A residual convolutional neural network was applied to generate full-dose from ultra-low-dose CT images. The quality of predicted CT images was assessed using root mean square error (RMSE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Scores ranging from 1 to 5 were assigned reflecting subjective assessment of image quality and related COVID-19 features, including ground glass opacities (GGO), crazy paving (CP), consolidation (CS), nodular infiltrates (NI), bronchovascular thickening (BVT), and pleural effusion (PE). The radiation dose in terms of CT dose index (CTDI The results demonstrated that the deep learning algorithm is capable of predicting standard full-dose CT images with acceptable quality for the clinical diagnosis of COVID-19 positive patients with substantial radiation dose reduction. • Ultra-low-dose CT imaging of COVID-19 patients would result in the loss of critical information about lesion types, which could potentially affect clinical diagnosis. • Deep learning-based prediction of full-dose from ultra-low-dose CT images for the diagnosis of COVID-19 could reduce the radiation dose by up to 89%. • Deep learning algorithms failed to recover the correct lesion structure/density for a number of patients considered outliers, and as such, further research and development is warranted to address these limitations.
Identifiants
pubmed: 32879987
doi: 10.1007/s00330-020-07225-6
pii: 10.1007/s00330-020-07225-6
pmc: PMC7467843
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1420-1431Subventions
Organisme : Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
ID : 320030_176052
Références
Wu Z, McGoogan JM (2020) Characteristics of and important lessons from the coronavirus disease 2019 (COVID-19) outbreak in China: summary of a report of 72314 cases from the Chinese Center for Disease Control and Prevention. JAMA. 323(13):1239–1242
doi: 10.1001/jama.2020.2648
Lai C-C, Shih T-P, Ko W-C, Tang H-J, Hsueh P-R (2020) Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and corona virus disease-2019 (COVID-19): the epidemic and the challenges. Int J Antimicrob Agents 55(3):105924
doi: 10.1016/j.ijantimicag.2020.105924
Tang Y-W, Schmitz JE, Persing DH, Stratton CW (2020) The laboratory diagnosis of COVID-19 infection: current issues and challenges. J Clin Microbiol 58(6):e00512–e00520
doi: 10.1128/JCM.00512-20
Kim H, Hong H, Yoon SH (2020) Diagnostic performance of CT and reverse transcriptase-polymerase chain reaction for coronavirus disease 2019: a meta-analysis. Radiology;201343
Bao C, Liu X, Zhang H, Li Y, Liu J (2020) COVID-19 computed tomography findings: a systematic review and meta-analysis. J Am Coll Radiol 17(6):701–709
doi: 10.1016/j.jacr.2020.03.006
Sakane H, Ishida M, Shi L et al (2020) Biological effects of low-dose chest CT on chromosomal DNA. Radiology 295(2):439–445
doi: 10.1148/radiol.2020190389
Rehani MM, Szczykutowicz TP, Zaidi H (2020) CT is still not a low-dose imaging modality. Med Phys 47(2):293–296
doi: 10.1002/mp.14000
Hsieh J, Nett B, Yu Z, Sauer K, Thibault J-B, Bouman CA (2013) Recent advances in CT image reconstruction. Curr Radiol Rep 1:39–51
doi: 10.1007/s40134-012-0003-7
Goo HW (2012) CT radiation dose optimization and estimation: an update for radiologists. Korean J Radiol 13(1):1–11
doi: 10.3348/kjr.2012.13.1.1
Zhao T, McNitt-Gray M, Ruan D (2019) A convolutional neural network for ultra-low-dose CT denoising and emphysema screening. Med Phys 46(9):3941–3950
doi: 10.1002/mp.13666
Radpour A, Bahrami-Motlagh H, Taaghi MT et al (2020) COVID-19 evaluation by low-dose high resolution CT scans protocol. Acad Radiol 27(6):901
doi: 10.1016/j.acra.2020.04.016
Agostini A, Floridi C, Borgheresi A 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
doi: 10.1007/s11547-020-01179-x
Kang Z, Li X, Zhou S (2020) Recommendation of low-dose CT in the detection and management of COVID-2019. Eur Radiol 30(8):4356–4357
doi: 10.1007/s00330-020-06809-6
Dangis A, Gieraerts C, Bruecker YD et al (2020) Accuracy and reproducibility of low-dose submillisievert chest CT for the diagnosis of COVID-19. Radiology Cardiothoracic Imaging 2:e200196
doi: 10.1148/ryct.2020200196
Baum U, Anders K, Steinbichler G et al (2004) Improvement of image quality of multislice spiral CT scans of the head and neck region using a raw data-based multidimensional adaptive filtering (MAF) technique. Eur Radiol 14:1873–1881
doi: 10.1007/s00330-004-2403-4
Wessling J, Esseling R, Raupach R et al (2007) The effect of dose reduction and feasibility of edge-preserving noise reduction on the detection of liver lesions using MSCT. Eur Radiol 17:1885–1891
doi: 10.1007/s00330-006-0545-2
Litjens G, Kooi T, Bejnordi BE et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88
doi: 10.1016/j.media.2017.07.005
Sahiner B, Pezeshk A, Hadjiiski LM et al (2019) Deep learning in medical imaging and radiation therapy. Med Phys 46:e1–e36
doi: 10.1002/mp.13264
Shiri I, Arabi H, Geramifar P et al (2020) Deep-JASC: joint attenuation and scatter correction in whole-body (18)F-FDG PET using a deep residual network. Eur J Nucl Med Mol Imaging. https://doi.org/10.1007/s00259-020-04852-5
Sanaat A, Arabi H, Mainta I, Garibotto V, Zaidi H (2020) Projection-space implementation of deep learning-guided low-dose brain PET imaging improves performance over implementation in image-space. J Nucl Med. https://doi.org/10.2967/jnumed.119.239327
Shiri I, AmirMozafari Sabet K, Arabi H et al (2020) Standard SPECT myocardial perfusion estimation from half-time acquisitions using deep convolutional residual neural networks. J Nucl Cardiol. https://doi.org/10.1007/s12350-020-02119-y
Yang Q, Yan P, Zhang Y et al (2018) Low-dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss. IEEE Trans Med Imaging 37:1348–1357
doi: 10.1109/TMI.2018.2827462
Kim B, Han M, Shim H, Baek J (2019) A performance comparison of convolutional neural network-based image denoising methods: the effect of loss functions on low-dose CT images. Med Phys 46:3906–3923
doi: 10.1002/mp.13713
Shin YJ, Chang W, Ye JC et al (2020) Low-dose abdominal CT using a deep learning-based denoising algorithm: a comparison with CT reconstructed with filtered back projection or iterative reconstruction algorithm. Korean J Radiol 21:356–364
doi: 10.3348/kjr.2019.0413
Gholizadeh-Ansari M, Alirezaie J, Babyn P (2020) Deep learning for low-dose CT denoising using perceptual loss and edge detection layer. J Digit Imaging 33(2):504–515
doi: 10.1007/s10278-019-00274-4
Christianson O, Winslow J, Frush DP, Samei E (2015) Automated technique to measure noise in clinical CT examinations. AJR Am J Roentgenol 205:W93–W99
doi: 10.2214/AJR.14.13613
Zeng D, Huang J, Bian Z et al (2015) A simple low-dose x-ray CT simulation from high-dose scan. IEEE Trans Nucl Sci 62(5):2226–2233
doi: 10.1109/TNS.2015.2467219
Li W, Wang G, Fidon L, Ourselin S, Cardoso MJ, Vercauteren T (2017) On the compactness, efficiency, and representation of 3D convolutional networks: brain parcellation as a pretext task. In: Niethammer M, Styner M, Aylward S et al (eds) Information Processing in Medical Imaging. Springer International Publishing, Cham, pp 348–360
doi: 10.1007/978-3-319-59050-9_28
Jones AK, O'Connor MK, Zaidi H (2019) The eventual rejection of the linear no-threshold theory will lead to a drastic reduction in the demand for diagnostic medical physics services. Med Phys 46:3325–3328
doi: 10.1002/mp.13619
Brenner DJ, Hricak H (2010) Radiation exposure from medical imaging: time to regulate? JAMA 304:208–209
doi: 10.1001/jama.2010.973
Abdollahi H, Shiri I, Salimi Y et al (2016) Radiation dose in cardiac SPECT/CT: An estimation of SSDE and effective dose. Eur J Radiol 85:2257–2261
doi: 10.1016/j.ejrad.2016.10.021
NAS/NRC (National Academy of Sciences/National Research Council) (2006) Health risks from exposure to low levels of ionizing radiation: BEIR VII – Phase 2BEIR VII phase. National Research Council, Washington DC
(2007) The 2007 Recommendations of the International Commission on Radiological Protection. ICRP publication 103