Artificial intelligence in lung cancer screening: assessment of the diagnostic accuracy of the algorithm analyzing low-dose computed tomography
https://doi.org/10.21292/2075-1230-2020-98-8-24-31
Abstract
The diagnostic accuracy of the artificial intelligence algorithm aimed to detect lesions on low-dose computer tomograms has been independently assessed. The dataset formed as part of the lung cancer screening program in Moscow was used. The following indicators have been defined: sensitivity – 0.817%, specificity – 0.925%, accuracy – 0.860%, area under the characteristic curve – 0.930. High accuracy rates demonstrated through the independent assessment indicate a good reproducibility of the results by artificial intelligence using independent data about the population of Moscow
About the Authors
S. P. Morozov
Moscow Scientific Practical Clinical Center for Diagnostics and Telemedical Technology
Russian Federation
Russian Federation
Sergey P. Morozov, Director
Build. 1, 16/26 Raskovoy St., Moscow, 125040
Phone: +7 (495) 276-04-36
A. V. Vladzimirskiy
Moscow Scientific Practical Clinical Center for Diagnostics and Telemedical Technology
Russian Federation
Russian Federation
Anton V. Vladzimirskiy, Deputy Director for Research
Build. 1, 16/26 Raskovoy St., Moscow, 125040
Phone: +7 (495) 670-74-80, ext. 2204V. A. Gombolevskiy
Moscow Scientific Practical Clinical Center for Diagnostics and Telemedical Technology
Russian Federation
Russian Federation
Viktor A. Gombolevskiy, Head of Department for Radiology Quality Development
Build. 1, 16/26 Raskovoy St., Moscow, 125040
Phone: +7 (495) 276-04-36
V. G. Klyashtorny
Moscow Scientific Practical Clinical Center for Diagnostics and Telemedical Technology
Russian Federation
Russian Federation
Vladislav G. Klyashtorny, Analyst of Research Coordination Department
Build. 1, 16/26 Raskovoy St., Moscow, 125040
Phone: +7 (495) 276-04-36
I. A. Fedulova
Philips Innovation Labs Rus
Russian Federation
Russian Federation
Irina A. Fedulova, Leading Specialist
Office 1069, Floor 3, Build. 1, 42, Bolshoy Bul., Skolkovo Innovation Center, Moscow, 143026
L. A. Vlasenkov
Philips Innovation Labs Rus
Russian Federation
Russian Federation
Leonid A. Vlasenkov, Researcher
Office 1069, Floor 3, Build. 1, 42, Bolshoy Bul., Skolkovo Innovation Center, Moscow, 143026
Phone: +7 (495) 922-25-85
References
1. Gombolevskiy V.А., Barchuk А.А., Laypan А.Sh., Vetsheva N.N., Vladzimirskiy А.V., Morozov S.P. Organization and efficiency of screening for malignant lung tumors by low-dose computed tomography. Radiologiya-Praktika, 2018, no. 1 (67), pp. 28-36. (In Russ.)
2. Morozov S.P., Vladzimirskiy А.V., Klyashtorny V.G., Аndreychenko А.E., Kulberg N.S., Gombolevskiy V.А. Klinicheskie ispytaniya programmnogo obespecheniya na osnove intellektualnykh tekhnologiy (luchevaya diagnostika). Preprint № TSDT-2019-1 / Seriya Luchshie praktiki luchevoy i instrumentalnoy diagnostiki. [A clinical acceptance of software based on artificial intelligence technologies (radiology). Preprint No CDT-2019-1 / Series of Best practices in medical imaging]. 2019, Iss., 23, 33 p.
3. Morozov S.P., Gombolevskiy V.А., Vladzimirskiy А.V., Laypan А.Sh., Kononets P.V., Dreval P.А. Results of the first year of screening for lung cancer using low-dose computed tomography in Moscow. Voprosy Onkologii, 2019, vol. 65, no. 2, pp. 224-233. (In Russ.)
4. Tyurin I.E. X-ray diagnostics in the Russian Federation in 2014. Vestnik Rentgenologii i Radiologii, 2015, no. 6, pp. 56-63. (In Russ.)
5. Shelekhov P.V. The efficacy of X-ray diagnostics in the regions of the Russian Federation. Menedzher Zdravookhraneniya, 2017, no. 5, pp. 33-41. (In Russ.)
6. Schepin V.O. On the issue of staffing in the X-ray diagnostics units. Problemy Sotsialnoy Gigieny, Zdravookhraneniya i Istorii Meditsiny, 2014, vol. 22, no. 5, pp. 42-45. (In Russ.)
7. Al Mohammad B., Brennan P.C., Mello-Thoms C. A review of lung cancer screening and the role of computer-aided detection. Clin. Radiol., 2017, vol. 72, no. 6, pp. 433-442. doi: 10.1016/j.crad.2017.01.002.
8. Benzaquen J., Boutros J., Marquette C., Delingette H., Hofman P. Lung cancer screening, towards a multidimensional approach: why and how? Cancers (basel), 2019, Feb. 12; 11(2). pii: E212. doi: 10.3390/cancers11020212.
9. Causey J.L., Guan Y., Dong W., Walker K., Qualls J.A., Prior F., Huang X. Lung cancer screening with low-dose CT scans using a deep learning approach. arXiv:1906.00240 [eess.IV].
10. Chun I.Y., Zheng X., Long Y., Fessler J.A. BCD-Net for Low-dose CT reconstruction: acceleration, convergence, and generalization. arXiv:1908.01287 [eess.IV].
11. Ciompi F., Chung K., van Riel S.J., Setio A.A.A. Towards automatic pulmonary nodule management in lung cancer screening with deep learning. Sci. Rep., 2017, no. 7, pp. 46479. doi: 10.1038/srep46479.
12. De Koning H.J., Van Der Aalst C.M., Ten Haaf K., Oudkerk М. Effects of volume CT lung cancer screening: mortality results of the NELSON randomised-controlled population based trial. J. Thorac. Oncol., 2018, no. 13, pp. S185. doi: 10.1016/j.jtho.2018.08.012.
13. Huang K.L., Wang S.Y., Lu W.C., Chang Y.H., Su J., Lu Y.T. Effects of low-dose computed tomography on lung cancer screening: a systematic review, meta-analysis, and trial sequential analysis. BMC Pulm. Med., 2019, vol. 19, no. 1, pp. 126. doi: 10.1186/s12890-019-0883-x.
14. Lei Y., Tian Y., Shan H., Zhang J., Wang G., Kalra M. Soft activation mapping of lung nodules in low-dose CT images. arXiv:1810.12494.
15. Liu Y., Luo H., Qing H., Wang X., Ren J., Xu G., Hu S., He C., Zhou P. Screening baseline characteristics of early lung cancer on low-dose computed tomography with computer-aided detection in a Chinese population. Cancer Epidemiol., 2019, no. 62, pp. 101567, doi: 10.1016/j.canep.2019.101567.
16. Liu X., Zhou H., Hu Z., Jin Q., Wang J., Ye B. Clinical Application of Artificial Intelligence Recognition Technology in the Diagnosis of Stage T1 Lung Cancer. Zhongguo Fei Ai Za Zhi, 2019, vol. 22, no. 5, pp. 319-323. doi: 10.3779/j.issn.1009-3419.2019.05.09.
17. Morozov S.P., Vladzymyrskyy A.V., Klyashtornyy V.G., Andreychenko A.E., Kulberg N.S., Gombolevsky V. A clinical acceptance of software based on artificial intelligence technologies (radiology). Preprint No CDT-2019-1. Series Best practices in medical imaging. issue 23, Moscow, 2019. 27 p. arXiv:1908.00381.
18. National Lung Screening Trial Research Team. Lung cancer incidence and mortality with extended follow-up in the National Lung Screening Trial. J. Thorac. Oncol., 2019, Jun. 28. pii: S1556-0864(19)30473-3. doi: 10.1016/j.jtho.2019.05.044.
19. Pastorino U., Sverzellati N., Sestini S., Silva M., Sabia F., Boeri M., Cantarutti A., Sozzi G., Corrao G., Marchianò A. Ten-year results of the multicentric Italian lung detection trial demonstrate the safety and efficacy of biennial lung cancer screening. Eur. J. Cancer, 2019, no. 118, pp. 142-148. doi: 10.1016/j.ejca.2019.06.009.
20. Polat G., Halici U., Dogrusoz Y.S. False positive reduction in lung computed tomography images using convolutional neural networks. arXiv:1811.01424.
21. Ranschaert E.R., Morozov S.P., Algra P.R. Artificial intelligence in medical imaging. Springer International Publishing. 2019, 373 p.
22. Suzuki K., Li F., Sone S., Doi K. Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artificial neural network. IEEE Trans Med Imaging, 2005, vol. 24, no. 9, pp. 1138-1150.
23. Trajanovski S., Mavroeidis D., Swisher C. L., Gebre B. G., Veeling B. S., Wiemker R., Klinder T., Tahmasebi A., Regis S.M., Wald C., McKee B. J., Flacke S., MacMahon H., Pien H. Towards radiologist-level cancer risk assessment in CT lung screening using deep learning. arXiv:1804.01901v2 [cs.CV] 11 Apr. 2019.
24. You C., Yang L., Zhang Y., Wang G. Low-dose CT via deep CNN with skip connection and network in network. arXiv:1811.10564.
25. Zhang Y., Rong J., Lu H., Xing Y., Meng J. Low-dose lung CT image restoration using adaptive prior features from full-dose training database. IEEE Trans. Med. Imaging, 2017, vol. 36, no. 12, pp. 2510-2523. doi: 10.1109/TMI.2017.2757035. Epub 2017 Sep. 27.
Review
For citations:
Morozov S.P., Vladzimirskiy A.V., Gombolevskiy V.A., Klyashtorny V.G., Fedulova I.A., Vlasenkov L.A. Artificial intelligence in lung cancer screening: assessment of the diagnostic accuracy of the algorithm analyzing low-dose computed tomography. Tuberculosis and Lung Diseases. 2020;98(8):24-31. (In Russ.) https://doi.org/10.21292/2075-1230-2020-98-8-24-31
Views:
1310
Email this article 