Artificial intelligence in tuberculosis detection. Opportunities and prospects

DOI: https://doi.org/10.29296/25877305-2020-05-06
Download full text PDF
Issue: 
5
Year: 
2020

Professor E. Borodulina, MD Samara State Medical University

In the period of global digitalization of medicine, one of the promising areas is the organization of population screening with artificial intelligence (AI), above all, for socially significant diseases. In our country, these are annual fluorographic examinations for tuberculosis. The transition to digital fluorography has already predetermined positive trends in a systematic approach to the timely detection of tuberculosis. The prospects for further improvement of screening for tuberculosis are determined primarily by the need for a systematic approach to routine repetitive studies, which involves the use of AI to recognize the disease, to select and form groups for further examination by a medical specialist. Whether this is possible in the near future and how the creation of AI is going on is discussed in this review.
Keywords: 
artificial intelligence
tuberculosis
screening
recognition

It appears your Web browser is not configured to display PDF files. Download adobe Acrobat или click here to download the PDF file.

References: 
  1. Miroshnichenko S.I., Kovalenko Ju.N., Chernetsov V.B. Zamena fljuorografii na skriningovuju tsifrovuju rentgenografiju. Poliklinika. 2016; 6: 19–22 [Miroshnichenko S.I., Kovalenko Yu.N., Chernetsov V.B. Zamena flyuorografii na skriningovuyu tsifrovuyu rentgenografiyu. Poliklinika. 2016; 6: 19–22 (in Russ.)].
  2. Starshinova A.A., Kudlaj D.A., Dovgaljuk I.F. i dr. Effektivnost' primenenija novyh metodov immunodiagnostiki tuberkuleznoj infektsii v Rossijskoj Federatsii. Pediatrija. 2019; 98 (4): 229–35 [Starshinova A.A., Kudlay D.A., Dovgalyuk I.F. et al. Efficacy of new methods of tuberculosis infection immunodiagnostics in the Russian Federation. Pediatria. 2019; 98 (4): 229-235 (in Russ.)]. DOI: 10.24110/0031-403X-2019-98-4-229-235
  3. Slogotskaja L.V., Sinitsyn M.V., Kudlaj D.A. Vozmozhnosti immunologicheskih testov v diagnostike latentnoj tuberkuleznoj infektsii i tuberkuleza. Tuberkulez i bolezni legkih. 2019; 97 (11): 46–58 [Slogotskaya L.V., Sinitsyn M.V., Kudlay D.A. Potentialities of immunological tests in the diagnosis of latent tuberculosis infection and tuberculosis. Tuberculosis and Lung Diseases. 2019; 97 (11): 46–58 (in Russ.)]. DOI: 10.21292/2075-1230-2019-97-11-46-58
  4. Kakanov O.G. Osobennosti fljuorograficheskogo vyjavlenija tuberkuleza legkih. Bjulleten' meditsinskih internet-konferentsij. 2018; 8 (4): 159 [Kakanov O.G. Osobennosti flyuorograficheskogo vyyavleniya tuberkuleza legkikh. Byulleten’ meditsinskikh internet-konferentsii. 2018; 8 (4): 159 (in Russ.)].
  5. Zubova N.A. Effektivnost' massovyh profilakticheskih osmotrov v sub'ektah rossijskoj federatsii s nizkim urovnem zabolevaemosti tuberkulezom. Sotsial'nye aspekty zdorov'ja naselenija. 2016; 4 (50): 8 [Zubova N.A. Effectiveness of mass preventive examinations in subjects of the russian federation with low morbidity rates of tuberculosis. Sotsial’nye aspekty zdorov’ya naseleniya. 2016; 4 (50): 8 (in Russ.)]. DOI: 10.21045/2071-5021-2016-50-4-8. URL: http://vestnik.mednet.ru/content/view/767/30/
  6. Behterev A.V., Labusov V.A., Put'makov A.N. i dr. O fljuorografii, tsifrovoj rentgenografii, skrininge i effektivnosti. Poliklinika. 2019; 1–1: 17–20 [Bekhterev A.V., Labusov V.A., Put’makov A.N. et al. O flyuorografii, tsifrovoi rentgenografii, skrininge i effektivnosti. Poliklinika. 2019; 1–1: 17–20 (in Russ.)].
  7. Xu Sh., Jahn W., Müller J.-D. CAD-based shape optimisation with CFD using a discrete adjoint. Numerical Methods in Fluids. 2014; 74 (3): 153-68. DOI: 10.1002/fld.3844
  8. Khan F.A., Pande T., Song R. et al. Computer-aided reading of tuberculosis chest radiography: moving the research agenda forward to inform policy. Eur. Respir. J. 2017; 50: 1700953; DOI: 10.1183/13993003.00953-2017
  9. Jaeger S., Karargyris A., Antani S. et al. Detecting tuberculosis in radiographs using combined lung masks. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Conference Proceedings. 2012; 2012: 4978–81. DOI: 10.1109/EMBC.2012.6347110
  10. Vajda S., Karargyris A., Jaeger S. et al. Feature Selection for Automatic Tuberculosis Screening in Frontal Chest Radiographs. J. Med. Syst. 2018; 42 (8): 146. DOI: 10.1007/s10916-018-0991-9
  11. Pande T., Cohen C., Pai M. et al. Computer-aided detection of pulmonary tuberculosis on digital chest radiographs: a systematic review. Int. J. Tuberc. Lung. Dis. 2016; 20 (9): 1226–30. DOI: 10.5588/ijtld.15.0926
  12. Rahman M., Codlin A., Rahman M. et al. An evaluation of automated chest radiography reading software for tuberculosis screening among public- and private-sector patients. Eur. Respir. J. 2017; 49 (5): 1602159. DOI: 10.1183/13993003.02159-2016
  13. Zaidi S., Habib S., Van Ginneken B. et al. Evaluation of the diagnostic accuracy of Computer-Aided Detection of tuberculosis on Chest radiography among private sector patients in Pakistan. Sci. Rep. 2018; 8 (1): 12339. DOI: 10.1038/s41598-018-30810-1
  14. Melendez J., Sánchez C., Philipsen R. et al. An automated tuberculosis screening strategy combining X-ray-based computer-aided detection and clinical information. Sci. Rep. 2016; 6: 25265. DOI: 10.1038/srep25265
  15. Hwang S., Kim H.-E., Jeong J. et al. A novel approach for tuberculosis screening based on deep convolutional neural networks. Proc. SPIE 9785, Medical Imaging 2016: Computer-Aided Diagnosis, 97852W (24 March 2016); https://doi.org/10.1117/12.2216198
  16. Lakhani P., Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017; 284 (2): 574–82. DOI: 10.1148/radiol.2017162326.
  17. Jaeger S., Juarez-Espinosa O., Candemir S. et al. Detecting drug-resistant tuberculosis in chest radiographs. Int. J. Comput. Assist. Radiol. Surg. 2018; 13 (12): 1915–25. DOI: 10.1007/s11548-018-1857-9