Automated analysis of lung lesions in COVID-19: comparison of standard and low-dose CT

Introduction. Chest computed tomography (CT) plays a prominent role in determining the extent of pulmonary parenchymal lesions in COVID-19. At the same time, subjectivity of lung lesion volume assessment using 0-4 CT scale in COVID-19 and gradual introduction of low-dose CT (LDCT) requires an investigation of semi-automated lung segmentation accuracy in LDCT compared to CT.

Study Objective. To compare the accuracy of affected lung tissue volume calculation between CT and LDCT in COVID-19 using a semi-automatic segmentation program.

Material and Methods. The retrospective study was performed on data from the earlier prospective multicenter study registered at ClinicalTrials.gov, NCT04379531. CT and LDCT data were processed in 3D Slicer software with Lung CT Segmenter and Lung CT Analyzer extensions, and the volume of affected lung tissue and lung volume were determined by thresholding.

Results. The sample size was 84 patients with signs of COVID-19-associated pneumonia. Mean age was 50.6 ± 13.3 years, and the median body mass index (BMI) was 28.15 [24.85; 31.31] kg/m2. The effective doses were 10.1 ± 3.26 mSv for the standard CT protocol and 2.64 mSv [1.99; 3.67] for the developed LDCT protocol. The analysis of absolute lung lesion volume in cubic centimeters with Wilcoxon Signed Ranks Test revealed a statistically significant difference between CT and LDCT (p-value < 0.001). No statistically significant differences were found in the relative values of lung tissue lesion volume (lesion volume/lung volume) between CT and LDCT using Wilcoxon Signed Ranks Test (p-value = 0.95).

Conclusion. The reliability of developed LDCT protocol in COVID-19 for the semi-automated calculation of affected tissue percentage was comparable to the standard chest CT protocol when using 3D Slicer with Lung CT Segmenter and Lung CT Analyzer extensions.

1. Lai C.-C., Shih T.-P., Ko W.-C., Tang H.-J., Hsueh P.-R. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and coronavirus disease-2019 (COVID-19): The epidemic and the challenges. Int. J. Antimicrob. Agents. 2020;55(3):105924. DOI: 10.1016/j.ijantimicag.2020.105924.

2. Вe Jaegere T.M.H., Krdzalic J., Fasen B.A.C.M., Kwee R.M.; COVID-19 CT Investigators South-East Netherlands (CISEN) study group. Radiological society of north america chest ct classification system for reporting COVID-19 pneumonia: Interobserver variability and correlation with reverse-transcription polymerase hain reaction. Radiol. Cardiothorac. Imaging. 2020;2(3):e200213. DOI: 10.1148/ryct.2020200213.

3. Samir A., El-Husseiny R.M., Sweed R.A., El-Maaboud N.A.E.-M.A., Masoud M. Ultra-low-dose chest CT protocol during the second wave of COVID-19 pandemic: A double-observer prospective study on 250 patients to evaluate its detection accuracy. Egypt. J. Radiol. Nucl. Med. 2021;52(1):136. DOI: 10.1186/s43055-021-00512-2.

4. Prokop M., van Everdingen W., van Rees Vellinga T., Quarles van Ufford H., Stöger L., Beenen L. et al. CO-RADS: A categorical СТ assessment scheme for patients suspected of having COVID-19-definition and evaluation. Radiol. 2020;296(2):E97–E104. DOI: 10.1148/radiol.2020201473.

5. Yang R., Li X., Liu H., Zhen Y., Zhang X., Xiong Q. et al. Chest ct severity score: An imaging tool for assessing severe covid-19. Radiol. Cardiothorac. Imaging. 2020;2(2):e200047. DOI: 10.1148/ryct.2020200047.

6. Colombi D., Bodini F.C., Petrini M., Maffi G., Morelli N., Milanese G. et al. Well-aerated lung on admitting chest CN to predict adverse outcome in COVID-19 pneumonia. Radiol. 2020;296(2):E86–E96. DOI: 10.1148/radiol.2020201433.

7. Priority medical devices list for the COVID-19 response and associated technical specifications: Interim guidance. URL: https://apps.who.int/iris/bitstream/handle/10665/336745/WHO-2019-nCoV-MedDev-TS-O2T.V2-eng.pdf (22.11.2022).

8. Lee E.Y.P, Ng M.Y., Khong P.L. COVID-19 pneumonia: what has CT taught us? Lancet Infect. Dis. 2020;20(4):384–385. DOI: 10.1016/S1473-3099(20)30134-1.

9. Xia T., Li J., Gao J., Xu X. Small solitary ground-glass nodule on СТ as an initial manifestation of coronavirus disease 2019 (COVID-19) pneumonia. Korean. J. Radiol. 2020;21(5):545. DOI:10.3348/kjr.2020.0240.

10. Li B., Li X., Wang Y., Han Y., Wang Y., Wang C. et al. Diagnostic value and key features of computed tomography in Coronavirus Disease 2019. Emerg. Microbes Infec. 2020;9(1):787–793. DOI: 10.1080/22221751.2020.1750307.

11. Parekh M., Donuru A., Balasubramanya R., Kapur S. Review of the chest CT differential diagnosis of ground-glass opacities in the COVID era. Radiol. 2020;297(3):E289–E302. DOI: 10.1148/radiol.2020202504.

12. Radiation diagnostics of coronavirus disease (COVID-19): organization, methodology, interpretation of results; 2nd ed. (In Russ.). URL: https:// tele-med.ai/biblioteka-dokumentov/luchevaya-diagnostika-koronavirusnoj-bolezni-covid-19-organizaciya-metodologiya-interpretaciya-rezultatov2 (22.11.2022)

13. Huang L., Han R., Ai T., Yu P., Kang H., Tao Q. et al. Serial quantitative chest СТ assessment of COVID-19: A deep learning approach. Radiol: Cardiothorac. Imaging. 2020;2(2):e200075. DOI: 10.1148/ ryct.2020200075.

14. Morozov S.P., Kuzmina E.S., Ledikhova N.V., Vladzymyrskyy A.V., Trofimenko I.A., Mokienko O.A. et al. Mobilizing the academic and practical potential of diagnostic radiology during the COVID-19 pandemic in Moscow. Digital Diagnostics. 2020;1(1):5–12. (In Russ.). DOI: 10.17816/DD51043.

15. Prasad K.N., Cole W.C., Haase G.M. Radiation protection in humans: Extending the concept of as low as reasonably achievable (Alara) from dose to biological damage. BJR. 2004;77(914):97–99. DOI: 10.1259/ bjr/88081058.

16. Preface, executive summary and glossary. Ann. ICRP. 2007;37(2–4):9– 34. DOI: 10.1016/j.icrp.2007.10.003.

17. Sakane H., Ishida M., Shi L., Fukumoto W., Sakai C., Miyata Y. et al. Biological effects of low-dose chest CT on chromosomal DNA. Radiology. 2020;295(2):439–445. DOI: 10.1148/radiol.2020190389.

18. Tofighi S., Najafi S., Johnston S.K., Gholamrezanezhad A. Low-dose CT in COVID-19 outbreak: Radiation safety, image wisely, and image gently pledge. Emerg. Radiol. 2020;27(6):601–605. DOI: 10.1007/s10140-02001784-3.

19. Tabatabaei S.M.H, Talari H., Gholamrezanezhad A., Farhood B., Rahimi H., Razzaghi R. et al. A low-dose chest CT protocol for the diagnosis of COVID-19 pneumonia: A prospective study. Emerg. Radiol. 2020;27(6):607–615. DOI: 10.1007/s10140-020-01838-6.

20. Schulze-Hagen M., Hübel C., Meier-Schroers M., Yüksel C., Sander A. et al. Low-dose chest CT for the diagnosis of COVID-19. Deutsches Ärzteblatt International. 2020;117(22–23):389–395. DOI: 10.3238/arztebl.2020.0389.

21. Aslan S., Bekçi T., Çakır İ.M., Ekiz M., Yavuz İ., Şahin A.M. Diagnostic performance of low-dose chest CT to detect COVID-19: A Turkish population study. Diagn. Interv. Radiol. 2021;27(2):181–187. DOI: 10.5152/dir.2020.20350.

22. Blokhin I., Gombolevskiy V., Chernina V., Gusev M., Gelezhe P., Aleshina O. et al. Inter-observer agreement between low-dose and standard-dose СТ with soft and sharp convolution kernels in СOVID-19 pneumonia. J. Clin. Med. 2022;11(3):669. DOI: 10.3390/jcm11030669.

23. Usanov M.S., Kulberg N.S., Morozov S.P. Development of anisotropic nonlinear noise-reduction algorithm for computed tomography data with context dynamic threshold. Computer Research and Modeling. 2019;11(2):233–248. (In Russ.). DOI: 10.20537/2076-7633-2019-11-2233-248.

24. Schilham A.M.R, van Ginneken B., Gietema H., Prokop M. Local noise weighted filtering for emphysema scoring of low-dose CT images. IEEE Trans. Med. Imaging. 2006;25(4):451–463. DOI: 10.1109/TMI.2006.871545.

25. Nikolaev A.E., Chernina V.Yu., Blokhin I.A., Shapiev A.N., Gonchar A.P., Gombolevskiy V.A. et al. The future of computer-aided diagnostics in chest computed tomography. Pirogov Russian Journal of Surgery. 2019;(12):91–99. (In Russ.). DOI: 10.17116/hirurgia201912191.

26. Bai T., Wang B., Nguyen D., Jiang S. Probabilistic self‐learning framework for low‐dose CT denoising. Med. Phys. 2021;48(5):2258–2270. DOI: 10.1002/mp.14796.

27. Tang C., Li J., Wang L., Li Z., Jiang L., Cai A. et al. Unpaired low-dose ct denoising network based on cycle-consistent generative adversarial network with prior image information. Comput. Math. Methods Med. 2019;2019:1–11. DOI: 10.1155/2019/8639825.

28. Gombolevskiy V., Morozov S., Chernina V., Blokhin I., Vassileva J. A phantom study to optimise the automatic tube current modulation for chest CT in COVID-19. Eur. Radiol. Exp. 2021;5(1):21. DOI: 10.1186/s41747-021-00218-0.

29. Maldjian P.D., Goldman A.R. Reducing radiation dose in body СТ: primer on dose metrics and key ct technical parameters. Am. Jour. of Rent. 2013;200(4):741–747. DOI: 10.2214/AJR.12.9768.

30. Gierada D.S., Bierhals A.J., Choong C.K., Bartel S.T., Ritter J.H., Das N.A. et al. Effects of CT section thickness and reconstruction kernel on emphysema quantification. Acad. Radiol. 2010;17(2):146–156. DOI: 10.1016/j.acra.2009.08.007.

31. Fedorov A., Beichel R., Kalpathy-Cramer J., Finet J., Fillion-Robin J.-C., Pujol S. et al. 3D slicer as an image computing platform for the Quantitative Imaging Network. Magn. Reson. Imaging. 2012;30(9):1323–1341. DOI: 10.1016/j.mri.2012.05.001.

32. Kikinis R., Pieper S.D., Vosburgh K.G. 3D slicer: F platform for subject-specific image analysis, visualization, and clinical support. In: F.A. Jolesz by ed. Intraoperative imaging andiImage-guided therapy. New York: Springer; 2014:277–289. DOI: 10.1007/978-1-4614-76573_19.

33. Bumm R., Lasso A., Kawel-Böhm N., Wäckerlin A., Ludwig P., Furrer M. First results of spatial reconstruction and quantification of COVID-19 chest CT infiltrates using lung CT analyzer and 3D slicer. Brit. J. Surg. 2021;108(4):znab202.077. DOI: 10.1093/bjs/znab202.077.

34. Kaza E., Dunlop A., Panek R., Collins D.J., Orton M., SymondsTayler R. et al. Lung volume reproducibility under ABC control and self-sustained breath-holding. J. Appl. Clin. Med. Phys. 2017;18(2):154– 162. DOI: 10.1002/acm2.12034.

35. Lanza E., Muglia R., Bolengo I., Santonocito O.G., Lisi C., Angelotti G. et al. Quantitative chest CT analysis in COVID-19 to predict the need for oxygenation support and intubation. Eur. Radiol. 2020;30(12):6770– 6778. DOI: 10.1007/s00330-020-07013-2.

36. Berta L., Rizzetto F., De Mattia C., Lizio D., Felisi M., Colombo P.E. et al. Automatic lung segmentation in COVID-19 patients: Impact on quantitative computed tomography analysis. Phys. Medica. 2021;87:115–122. DOI: 10.1016/j.ejmp.2021.06.001.

37. Ozsahin I., Sekeroglu B., Musa M.S., Mustapha M.T., Uzun Ozsahin D. Review on diagnosis of COVID-19 from chest CT images using artificial intelligence. Comput. Math. Methods in Med. 2020;2020:1–10. DOI: 10.1155/2020/9756518.

38. Shi F., Wang J., Shi J., Wu Z., Wang Q., Tang Z. et al. Review of artificial intelligence techniques in imaging data acquisition, segmentation, and diagnosis for covid-19. IEEE Rev. Biomed. Eng. 2021;14:4–15. DOI: 10.1109/RBME.2020.2987975.

39. Kulberg N.S., Reshetnikov R.V., Novik V.P., Elizarov A.B., Gusev M.A., Gombolevskiy V.A. et al. Inter-observer variability between readers of CT images: all for one and one for all. Digital Diagnostics. 2021;2(2):105– 118. (In Russ.). DOI: 10.17816/DD60622.

40. Boufarasse Y.B., Ettahir A., Bekkali D., Bennani J. Teleradiology and AI as solution to overcome the COVID-19 pandemic impact during the lockdowns in Africa. Health Sci. J. 2020;14(6):771. DOI: 10.36648/1791809X.14.6.771.

41. Tan B.S., Dunnick N.R., Gangi A., Goergen S., Jin Z.Y., Neri E. et al. RSNA International Trends: A global perspective on the COVID-19 pandemic and radiology in late 2020. Radiol. 2021;299(1):E193–E203. DOI: 10.1148/radiol.2020204267.

42. Martín-Noguerol T., Lopez-Ortega R., Ros P.R., Luna A. Teleworking beyond teleradiology: Managing radiology departments during the COVID-19 outbreak. Eur. Radiol. 2021;31(2):601–604. DOI: 10.1007/s00330-020-07205-w.