SCREENING FOR PULMONARY TUBERCULOSIS USING CHEST X-RAY WITH COMPUTER-AIDED DETECTION SYSTEMS: A LITERATURE REVIEW
Main Article Content
Abstract
Objective: To review the literature on pulmonary TB screening using automatic X-ray film reading
systems.
Subjects and methods: 13 publications from 2 databases MEDLINE and Cochrance in the period
from January 2010 to December 2021 were analyzed.
Results: Our study has shown that there are currently 12 automatic chest X-ray reading systems that
have been applied in screening for pulmonary tuberculosis. The sensitivities of the systems ranged
from 0.70 to 0.95 with specificities of 0.42 to 0.99, respectively. Of these, there are 3 systems that
achieve the sensitivity and specificity recommended by WHO for a TB screening tool (sensitivity
>=90% and specificity >=70%) namely: qXR, CAD4TB and INSIGHT CXR.
Conclusion: Our study has highlighted the overview and value of some AI software applications in
reading chest X-ray automatically supporting the diagnosis of pulmonary tuberculosis.
Article Details
Keywords
TB screening, Pulmonary tuberculosis, Chest X-ray, Computer-aided detection.
References
[1] “Global tuberculosis report 2020.” https://www.
who.int/publications/i/item/9789240013131
(accessed Apr. 16, 2021).
[2] Nguyen HV, “The second national tuberculosis
prevalence survey in Vietnam,” PLoS One, vol.
15, no. 4, p. e0232142, 2020, doi: 10.1371/
journal.pone.0232142.
[3] Li B, “Prevalence of pulmonary tuberculosis in
Tibet Autonomous Region, China, 2014,” Int J
Tuberc Lung Dis, vol. 23, no. 6, pp. 735–740,
Jun. 2019, doi: 10.5588/ijtld.18.0614.
[4] Law I, Floyd K, and African TB Prevalence
Survey Group, “National tuberculosis prevalence
surveys in Africa, 2008-2016: an overview of
results and lessons learned,” Trop Med Int Health,
vol. 25, no. 11, pp. 1308–1327, Nov. 2020, doi:
10.1111/tmi.13485.
[5] Migambi P, “Prevalence of tuberculosis in
Rwanda: Results of the first nationwide survey in
2012 yielded important lessons for TB control,”
PLoS One, vol. 15, no. 4, p. e0231372, 2020, doi:
10.1371/journal.pone.0231372.
[6] “World Health Organization: What is DOTS?:
a guide... - Google Scholar.” https://scholar.google.com/scholar_lookup?title=What
+is+DOTS?+A+Guide+to+Understanding+the+WHO%E2%80%94Recommended+TB+-
Control.+Strategy+Known+as+DOTS&publication_year=1999& (accessed Mar. 21, 2022).
[7] Qin ZZ, “Tuberculosis detection from chest
x-rays for triaging in a high tuberculosis-burden
setting: an evaluation of five artificial intelligence
algorithms,” The Lancet. Digital health, vol. 3,
no. 9, pp. e543–e554, Sep. 2021, doi: 10.1016/
s2589-7500(21)00116-3.
[8] Codlin AJ, “Independent evaluation of 12
artificial intelligence solutions for the detection
of tuberculosis,” Scientific reports, vol. 11, no. 1,
p. 23895, Dec. 2021, doi: 10.1038/s41598-021-
03265-0.
[9] Nash M, “Deep learning, computer-aided
radiography reading for tuberculosis: a diagnostic
accuracy study from a tertiary hospital in India,”
Scientific reports, vol. 10, no. 1, p. 210, Jan. 2020,
doi: 10.1038/s41598-019-56589-3.
[10] Habib SS, “Evaluation of computer aided
detection of tuberculosis on chest radiography
among people with diabetes in Karachi Pakistan,”
Scientific reports, vol. 10, no. 1, p. 6276, Apr.
2020, doi: 10.1038/s41598-020-63084-7.
[11] Murphy K, “Computer aided detection of
tuberculosis on chest radiographs: An evaluation
of the CAD4TB v6 system,” Scientific reports,
vol. 10, no. 1, p. 5492, Mar. 2020, doi: 10.1038/
s41598-020-62148-y.
[12] Khan FA, “Chest x-ray analysis with deep
learning-based software as a triage test for
pulmonary tuberculosis: a prospective study
of diagnostic accuracy for culture-confirmed
disease,” The Lancet. Digital health, vol. 2, no.
11, pp. e573–e581, Nov. 2020, doi: 10.1016/
s2589-7500(20)30221-1.
[13] Qin ZZ, “Using artificial intelligence to read chest
radiographs for tuberculosis detection: A multisite evaluation of the diagnostic accuracy of three
deep learning systems,” Scientific reports, vol. 9,
no. 1, p. 15000, Oct. 2019, doi: 10.1038/s41598-
019-51503-3.
[14] Zaidi SMA, “Evaluation of the diagnostic
accuracy of Computer-Aided Detection of
tuberculosis on Chest radiography among private
sector patients in Pakistan,” Scientific reports,
vol. 8, no. 1, p. 12339, Aug. 2018, doi: 10.1038/
s41598-018-30810-1.
[15] Melendez J, “Accuracy of an automated system
for tuberculosis detection on chest radiographs in
high-risk screening,” Int J Tuberc Lung Dis, vol.22, no. 5, pp. 567–571, May 2018, doi: 10.5588/
ijtld.17.0492.
[16] Rahman MT, “An evaluation of automated
chest radiography reading software for
tuberculosis screening among public- and
private-sector patients,” The European
respiratory journal, vol. 49, no. 5, May 2017, doi:
10.1183/13993003.02159-2016.
[17] Philipsen RH, “Automated chest-radiography as
a triage for Xpert testing in resource-constrained
settings: a prospective study of diagnostic
accuracy and costs,” Scientific reports, vol. 5, p.
12215, Jul. 2015, doi: 10.1038/srep12215.
[18] Muyoyeta M, “The sensitivity and specificity
of using a computer aided diagnosis program
for automatically scoring chest X-rays of
presumptive TB patients compared with Xpert
MTB/RIF in Lusaka Zambia,” PLoS One, vol.
9, no. 4, p. e93757, 2014, doi: 10.1371/journal.
pone.0093757.
[19] Breuninger M, “Diagnostic accuracy of computeraided detection of pulmonary tuberculosis in chest
radiographs: a validation study from sub-Saharan
Africa,” PLoS One, vol. 9, no. 9, p. e106381,
2014, doi: 10.1371/journal.pone.0106381.
who.int/publications/i/item/9789240013131
(accessed Apr. 16, 2021).
[2] Nguyen HV, “The second national tuberculosis
prevalence survey in Vietnam,” PLoS One, vol.
15, no. 4, p. e0232142, 2020, doi: 10.1371/
journal.pone.0232142.
[3] Li B, “Prevalence of pulmonary tuberculosis in
Tibet Autonomous Region, China, 2014,” Int J
Tuberc Lung Dis, vol. 23, no. 6, pp. 735–740,
Jun. 2019, doi: 10.5588/ijtld.18.0614.
[4] Law I, Floyd K, and African TB Prevalence
Survey Group, “National tuberculosis prevalence
surveys in Africa, 2008-2016: an overview of
results and lessons learned,” Trop Med Int Health,
vol. 25, no. 11, pp. 1308–1327, Nov. 2020, doi:
10.1111/tmi.13485.
[5] Migambi P, “Prevalence of tuberculosis in
Rwanda: Results of the first nationwide survey in
2012 yielded important lessons for TB control,”
PLoS One, vol. 15, no. 4, p. e0231372, 2020, doi:
10.1371/journal.pone.0231372.
[6] “World Health Organization: What is DOTS?:
a guide... - Google Scholar.” https://scholar.google.com/scholar_lookup?title=What
+is+DOTS?+A+Guide+to+Understanding+the+WHO%E2%80%94Recommended+TB+-
Control.+Strategy+Known+as+DOTS&publication_year=1999& (accessed Mar. 21, 2022).
[7] Qin ZZ, “Tuberculosis detection from chest
x-rays for triaging in a high tuberculosis-burden
setting: an evaluation of five artificial intelligence
algorithms,” The Lancet. Digital health, vol. 3,
no. 9, pp. e543–e554, Sep. 2021, doi: 10.1016/
s2589-7500(21)00116-3.
[8] Codlin AJ, “Independent evaluation of 12
artificial intelligence solutions for the detection
of tuberculosis,” Scientific reports, vol. 11, no. 1,
p. 23895, Dec. 2021, doi: 10.1038/s41598-021-
03265-0.
[9] Nash M, “Deep learning, computer-aided
radiography reading for tuberculosis: a diagnostic
accuracy study from a tertiary hospital in India,”
Scientific reports, vol. 10, no. 1, p. 210, Jan. 2020,
doi: 10.1038/s41598-019-56589-3.
[10] Habib SS, “Evaluation of computer aided
detection of tuberculosis on chest radiography
among people with diabetes in Karachi Pakistan,”
Scientific reports, vol. 10, no. 1, p. 6276, Apr.
2020, doi: 10.1038/s41598-020-63084-7.
[11] Murphy K, “Computer aided detection of
tuberculosis on chest radiographs: An evaluation
of the CAD4TB v6 system,” Scientific reports,
vol. 10, no. 1, p. 5492, Mar. 2020, doi: 10.1038/
s41598-020-62148-y.
[12] Khan FA, “Chest x-ray analysis with deep
learning-based software as a triage test for
pulmonary tuberculosis: a prospective study
of diagnostic accuracy for culture-confirmed
disease,” The Lancet. Digital health, vol. 2, no.
11, pp. e573–e581, Nov. 2020, doi: 10.1016/
s2589-7500(20)30221-1.
[13] Qin ZZ, “Using artificial intelligence to read chest
radiographs for tuberculosis detection: A multisite evaluation of the diagnostic accuracy of three
deep learning systems,” Scientific reports, vol. 9,
no. 1, p. 15000, Oct. 2019, doi: 10.1038/s41598-
019-51503-3.
[14] Zaidi SMA, “Evaluation of the diagnostic
accuracy of Computer-Aided Detection of
tuberculosis on Chest radiography among private
sector patients in Pakistan,” Scientific reports,
vol. 8, no. 1, p. 12339, Aug. 2018, doi: 10.1038/
s41598-018-30810-1.
[15] Melendez J, “Accuracy of an automated system
for tuberculosis detection on chest radiographs in
high-risk screening,” Int J Tuberc Lung Dis, vol.22, no. 5, pp. 567–571, May 2018, doi: 10.5588/
ijtld.17.0492.
[16] Rahman MT, “An evaluation of automated
chest radiography reading software for
tuberculosis screening among public- and
private-sector patients,” The European
respiratory journal, vol. 49, no. 5, May 2017, doi:
10.1183/13993003.02159-2016.
[17] Philipsen RH, “Automated chest-radiography as
a triage for Xpert testing in resource-constrained
settings: a prospective study of diagnostic
accuracy and costs,” Scientific reports, vol. 5, p.
12215, Jul. 2015, doi: 10.1038/srep12215.
[18] Muyoyeta M, “The sensitivity and specificity
of using a computer aided diagnosis program
for automatically scoring chest X-rays of
presumptive TB patients compared with Xpert
MTB/RIF in Lusaka Zambia,” PLoS One, vol.
9, no. 4, p. e93757, 2014, doi: 10.1371/journal.
pone.0093757.
[19] Breuninger M, “Diagnostic accuracy of computeraided detection of pulmonary tuberculosis in chest
radiographs: a validation study from sub-Saharan
Africa,” PLoS One, vol. 9, no. 9, p. e106381,
2014, doi: 10.1371/journal.pone.0106381.