Expert consensus on the application of artificial intelligence assisted image reading technology in the detection of pulmonary tuberculosis patients in chest imaging examination

doi:10.19982/j.issn.1000-6621.20250234

Abstract

Abstract:

Thoracic imaging is an important tool for the screening and diagnosis of tuberculosis. With the development of computer-aided detection (CAD) technology, new opportunities have emerged for the active finding of tuberculosis using thoracic imaging. This consensus was jointly developed by Imaging Professional Branch of Chinese Antituberculosis Association;Society of Tuberculosis, Chinese Medical Association; Standardization Professional Branch of Chinese Antituberculosis Association and Tuberculosis Control Professional Branch of Chinese Antituberculosis Association. It was supported by the Chinese Journal of Antituberculosis Publishing House and has been registered on the international practice guideline platform. The development of this consensus followed methodological principles, involving collaboration among experts from multiple fields and combining the World Health Organization’s relevant technical guidelines with the experiences of practical in China. The consensus explains the working principles of CAD, introduces the performance of 15 domestic and international CAD software programs for tuberculosis based on chest X-ray films (CXR), provides recommendations for the application of CXR-CAD in tuberculosis screening among patients visiting medical institutions as well as population with high risk of tuberculosis in communities, describes the research progress of CT based CAD in the diagnosis of tuberculosis, and highlights the current limitations of CAD in the active finding of tuberculosis patients and future research priorities.

Key words: Tuberculosis, pulmonary, Artificial intelligence, Computer-aided detection, Chest X-ray, Chest computed tomography, Expert consensus

CLC Number:

R81
R521

Imaging Professional Branch of Chinese Antituberculosis Association , Society of Tuberculosis, Chinese Medical Association , Standardization Professional Branch of Chinese Antituberculosis Association , Tuberculosis Control Professional Branch of Chinese Antituberculosis Association . Expert consensus on the application of artificial intelligence assisted image reading technology in the detection of pulmonary tuberculosis patients in chest imaging examination[J]. Chinese Journal of Antituberculosis, 2025, 47(9): 1093-1104. doi: 10.19982/j.issn.1000-6621.20250234

Figures/Tables 3

References 63

[1]	Hwang EJ, Jeong WG, David PM, et al. AI for detection of tuberculosis: implications for global health. Radiol Artif Intell, 2024, 6(2):e230327. doi:10.1148/ryai.230327.
[2]	World Health Organization. Chest radiography in tuberculosis detection: summary of current WHO recommendations and guidance on programmatic approaches. Geneva: World Health Organization, 2016.
[3]	World Health Organization. WHO consolidated guidelines on tuberculosis: module 2: screening: systematic screening for tuberculosis disease. Geneva: World Health Organization, 2021.
[4]	Stop TB Partnership and FIND. AI products for tuberculosis healthcare[EB/OL].[2025-04-06]. https://www.ai4hlth.org/products/.
[5]	Qin ZZ, Van der Walt M, Moyo S, et al. Computer-aided detection of tuberculosis from chest radiographs in a tuberculosis prevalence survey in South Africa: external validation and modelled impacts of commercially available artificial intelligence software. Lancet Digit Health, 2024, 6(9):e605-e613. doi:10.1016/S2589-7500(24)00118-3.
[6]	国家疾病预防控制局, 国家卫生健康委员会, 国家发展和改革委员会, 等. 关于印发《全国结核病防治规划(2024—2030年)》的通知[EB/OL].(2024-11-28)[2025-03-28]. https://www.gov.cn/zhengce/zhengceku/202412/content_6991217.htm.
[7]	李多, 吕平欣. 推动人工智能技术在肺结核影像领域的发展和运用. 中国防痨杂志, 2024, 46(3):253-259. doi:10.19982/j.issn.1000-6621.20240013.
[8]	Elliott A, Pirruccello JP. Machine learning-based markers for CAD. Lancet, 2023, 402(10397):182-183. doi:10.1016/S0140-6736(23)01061-9. pmid: 37453747
[9]	Chan HP, Hadjiiski LM, Samala RK. Computer-aided diagnosis in the era of deep learning. Med Phys, 2020, 47(5):e218-e227. doi:10.1002/mp.13764.
[10]	Takahashi R, Kajikawa Y. Computer-aided diagnosis: a survey with bibliometric analysis. Int J Med Inform, 2017, 101:58-67. doi:10.1016/j.ijmedinf.2017.02.004. pmid: 28347448
[11]	Zhang L, Weng TP, Wang HY, et al. Patient pathway analysis of tuberculosis diagnostic delay: a multicentre retrospective cohort study in China. Clin Microbiol Infect, 2021, 27(7): 1000-1006. doi:10.1016/j.cmi.2020.12.031.
[12]	国家呼吸内科医疗质量控制中心, 中华医学会结核病学分会, 中国防痨协会结核病控制专业分会, 等. 综合医疗机构肺结核早期发现临床实践指南. 结核与肺部疾病杂志, 2024, 5(1): 1-14. doi:10.19982/j.issn.1000-6621.20230428.
[13]	王艳, 洪创跃, 房宏霞, 等. 综合医疗机构呼吸科住院患者结核病筛查的研究. 中华结核和呼吸杂志, 2022, 45(12):1209-1213. doi:10.3760/cma.j.cn112147-20220720-00613.
[14]	Yang Y, Xia L, Liu P, et al. A prospective multicenter clinical research study validating the effectiveness and safety of a chest X-ray-based pulmonary tuberculosis screening software JF CXR-1 built on a convolutional neural network algorithm. Front Med (Lausanne), 2023, 10:1195451. doi:10.3389/fmed.2023.1195451.
[15]	Qin ZZ, Ahmed S, Sarker MS, et al. Tuberculosis detection from chest X-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms. Lancet Digit Health, 2021, 3: e543-e554. doi:10.1016/S2589-7500(21)00116-3.
[16]	Nabulsi Z, Sellergren A, Jamshy S, et al. Deep learning for distinguishing normal versus abnormal chest radiographs and generalization to two unseen diseases tuberculosis and COVID-19. Sci Rep, 2021, 11(1):15523. doi:10.1038/s41598-021-93967-2. pmid: 34471144
[17]	许杰, 王小义, 夏丽, 等. 基于人工智能的远程肺结核影像辅助诊断应用研究. 中国数字医学, 2021, 16(8):98-100. doi:10.3969/j.issn.1673-7571.2021.08.023.
[18]	Choi SY, Choi A, Baek SE, et al. Effect of multimodal diagnostic approach using deep learning-based automated detection algorithm for active pulmonary tuberculosis. Sci Rep, 2023, 13(1):19794. doi:10.1038/s41598-023-47146-0.
[19]	Nijiati M, Zhang Z, Abulizi A, et al. Deep learning assistance for tuberculosis diagnosis with chest radiography in low-resource settings. J Xray Sci Technol, 2021, 29(5):785-796. doi:10.3233/XST-210894.
[20]	熊章龙, 苏东红, 莫启章, 等. 广西基层医疗卫生机构卫生技术人员职业能力现状及岗位能力需求的调查与思考. 养生保健指南, 2021(36):287-288.
[21]	陈曦, 贺晓新, 高志东, 等. 北京市区(县)社区结核病防治医务人员工作现状调查结果评价. 中国防痨杂志, 2015, 37(2):183-188. doi:10.3969/j.issn.1000-6621.2015.02.013.
[22]	梁胜翔. 我国西部地区基层医疗卫生机构基本公共卫生服务人员核心能力建设研究. 重庆:中国人民解放军陆军军医大学, 2020. doi:10.27001/d.cnki.gtjyu.2020.000024.
[23]	Innes AL, Martinez A, Gao X, et al. Computer-aided detection for chest radiography to improve the quality of tuberculosis diagnosis in vietnam’s district health facilities: an implementation study. Trop Med Infect Dis, 2023, 8(11):488. doi:10.3390/tropicalmed8110488.
[24]	Tavaziva G, Harris M, Abidi SK, et al. Chest X-ray analysis with deep learning-based software as a triage test for pulmonary tuberculosis: an individual patient data meta-analysis of diagnostic accuracy. Clin Infect Dis, 2022, 74(8):1390-1400. doi:10.1093/cid/ciab639.
[25]	中华人民共和国医师法[EB/OL]. (2021-08-20)[2025-03-28]. http://www.npc.gov.cn/npc/c2/c30834/202108/t20210820_313104.html.
[26]	Park J, Hwang EJ, Lee JH, et al. Identification of active pulmonary tuberculosis among patients with positive interferon-gamma release assay results: value of a deep learning-based computer-aided detection system in different scenarios of implementation. J Thorac Imaging, 2023, 38(3):145-153. doi:10.1097/RTI.0000000000000691.
[27]	Mezrich JL. Is artificial intelligence (ai) a pipe dream? why legal issues present significant hurdles to AI autonomy. AJR Am J Roentgenol, 2022, 219(1):152-156. doi:10.2214/AJR.21.27224.
[28]	Jaremko JL, Azar M, Bromwich R, et al. Canadian association of radiologists white paper on ethical and legal issues related to artificial intelligence in radiology. Can Assoc Radiol J, 2019, 70(2):107-118. doi:10.1016/j.carj.2019.03.001. pmid: 30962048
[29]	Hwang EJ, Goo JM, Yoon SH, et al. Use of artificial intelligence-based software as medical devices for chest radiography: a position paper from the Korean society of thoracic radiology. Korean J Radiol, 2021, 22(11):1743-1748. doi:10.3348/kjr.2021.0544. pmid: 34564966
[30]	Yuen CM, Puma D, Millones AK, et al. Identifying barriers and facilitators to implementation of community-based tuberculosis active case finding with mobile X-ray units in Lima, Peru: a RE-AIM evaluation. BMJ Open, 2021, 11(7): e050314. doi:10.1136/bmjopen-2021-050314.
[31]	Okada K, Yamada N, Takayanagi K, et al. Applicability of artificial intelligence-based computer-aided detection (AI-CAD) for pulmonary tuberculosis to community-based active case finding. Trop Med Health, 2024, 52(1): 2. doi:10.1186/s41182-023-00560-6.
[32]	Dakulala P, Kal M, Honjepari A, et al. Evaluation of a population-wide, systematic screening initiative for tuberculosis on Daru island, Western Province, Papua New Guinea. BMC Public Health, 2024, 24(1): 959. doi:10.1186/s12889-024-17918-y. pmid: 38575948
[33]	王晓林, 王晓炜, 雷娟, 等. 宁夏回族自治区肺结核人工智能影像筛查系统的应用. 中国数字医学, 2020, 15(4): 39-41. doi:10.3969/j.issn.1673-7571.2020.04.012.
[34]	Codlin AJ, Dao TP, Vo LNQ, et al. Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis. Sci Rep, 2021, 11(1): 23895. doi:10.1038/s41598-021-03265-0. pmid: 34903808
[35]	Wali A, Safdar N, Manair R, et al. Early TB case detection by community-based mobile X-ray screening and Xpert testing in Balochistan. Public Health Action, 2021, 11(4): 174-179. doi:10.5588/pha.21.0050. pmid: 34956844
[36]	Velen K, Sathar F, Hoffmann CJ, et al. Digital chest X-ray with computer-aided detection for tuberculosis screening within correctional facilities. Ann Ame Thoracic Society, 2022, 19(8): 1313-1319. doi:10.1513/AnnalsATS.202103-380OC.
[37]	Jordan AM, Podewils LJ, Castro KG, et al. Prevalence and risk factors of tuberculosis disease in South African correctional facilities in 2015. Int J Tuberc Lung Dis, 2019, 23(11):1198-1204. doi:10.5588/ijtld.18.0782. pmid: 31718756
[38]	World Health Organization, UNICEF/UNDP/World Bank/WHO Special Programme for Research and Training in Tropical Diseases. Determining the local calibration of computer-assisted detection (CAD) thresholds and other parameters: a toolkit to support the effective use of CAD for TB screening. Geneva: World Health Organization, 2021.
[39]	Vanobberghen F, Keter AK, Jacobs BKM, et al. Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms. ERJ Open Res, 2024, 10(1): 00508-02023. doi:10.1183/23120541.00508-2023.
[40]	Liao Q, Feng H, Li Y, et al. Evaluation of an artificial intelligence (AI) system to detect tuberculosis on chest X-ray at a pilot active screening project in Guangdong, China in 2019. J Xray Sci Technol, 2022, 30(2):221-230. doi:10.3233/XST-211019.
[41]	Fehr J, Konigorski S, Olivier S, et al. Computer-aided interpretation of chest radiography reveals the spectrum of tuberculosis in rural South Africa. NPJ Digit Med, 2021, 4(1): 106. doi:10.1038/s41746-021-00471-y. pmid: 34215836
[42]	Koesoemadinata RC, Kranzer K, Livia R, et al. Computer-assisted chest radiography reading for tuberculosis screening in people living with diabetes mellitus. Int J Tuberc Lung Dis, 2018, 22(9): 1088-1094. doi:10.5588/ijtld.17.0827. pmid: 30092877
[43]	Habib SS, Rafiq S, Zaidi SMA, et al. Evaluation of computer aided detection of tuberculosis on chest radiography among people with diabetes in Karachi Pakistan. Sci Rep, 2020, 10(1): 6276. doi:10.1038/s41598-020-63084-7. pmid: 32286389
[44]	Kagujje M, Kerkhoff AD, Nteeni M, et al. The performance of computer-aided detection digital chest X-ray reading technolo-gies for triage of active tuberculosis among persons with a history of previous tuberculosis. Clin Infect Dis, 2023, 76(3): e894-e901. doi:10.1093/cid/ciac679.
[45]	Crowder R, Thangakunam B, Andama A, et al. Diagnostic accuracy of TB screening tests in a prospective multinational cohort: chest-X-ray with computer-aided detection, Xpert TB host response, and C-reactive protein. Clin Infect Dis, 2024, 7:ciae549. doi:10.1093/cid/ciae549.
[46]	Scott AJ, Limbada M, Perumal T, et al. Integrating molecular and radiological screening tools during community-based active case-finding for tuberculosis and COVID-19 in southern Africa. Int J Infect Dis, 2024, 145:107081. doi:10.1016/j.ijid.2024.107081.
[47]	Gelaw SM, Kik SV, Ruhwald M, et al. Diagnostic accuracy of three computer-aided detection systems for detecting pulmonary tuberculosis on chest radiography when used for screening: analysis of an international, multicenter migrants screening study. PLoS Glob Public Health, 2023, 3(7): e0000402. doi:10.1371/journal.pgph.0000402.
[48]	Mungai B, Ong’angò J, Ku CC, et al. Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey. PLoS Glob Public Health, 2022, 2(11): e0001272. doi:10.1371/journal.pgph.0001272.
[49]	王前, 何金戈, 李玉红, 等. 人工智能自动阅片技术用于HIV/AIDS人群结核病主动筛查效果的研究. 中国防痨杂志, 2021, 43(6): 557-561. doi:10.3969/j.issn.1000-6621.2021.06.007.
[50]	Innes AL, Martinez A, Hoang GL, et al. Active case finding to detect symptomatic and subclinical pulmonary tuberculosis disease: implementation of computer-aided detection for chest radiography in Viet Nam. Western Pac Surveill Response J, 2024, 15(4):1-12. doi:10.5365/wpsar.2024.15.4.1118.
[51]	Nijiati M, Zhou R, Damaola M, et al. Deep learning based CT images automatic analysis model for active/non-active pulmonary tuberculosis differential diagnosis. Front Mol Biosc, 2022, 9:1086047. doi:10.3389/fmolb.2022.1086047.
[52]	Xu Z, Bagci U, Kubler A, et al. Computer-aided detection and quantification of cavitary tuberculosis from CT scans. Med Phys, 2013, 40(11):113701. doi:10.1118/1.4824979.
[53]	Ma L, Wang Y, Guo L, et al. Developing and verifying automatic detection of active pulmonary tuberculosis from multi-slice spiral CT images based on deep learning. J Xray Sci Technol, 2020, 28(5):939-951. doi:10.3233/XST-200662.
[54]	巩盼, 李星宇, 来坤, 等. 基于定量CT检测浸润性肺结核病变的可行性研究. 临床放射学杂志, 2024, 43(4):567-573. doi:10.13437/j.cnki.jcr.2024.04.021.
[55]	Nijiati M, Guo L, Abulizi A, et al. Deep learning and radiomics of longitudinal CT scans for early prediction of tuberculosis treatment outcomes. Eur J Radiol, 2023, 169:111180. doi:10.1016/j.ejrad.2023.111180.
[56]	Yan C, Wang L, Lin J, et al. A fully automatic artificial intelligence-based CT image analysis system for accurate detection, diagnosis, and quantitative severity evaluation of pulmonary tuberculosis. Eur Radiol, 2022, 32(4):2188-2199. doi:10.1007/s00330-021-08365-z.
[57]	Li Y, Xu Z, LYU X, et al. Radiomics analysis of lung CT for multidrug resistance prediction in active tuberculosis: a multicentre study. Eur Radiol, 2023, 33(9):6308-6317. doi:10.1007/s00330-023-09589-x. pmid: 37004571
[58]	Nijiati M, Guo L, Tuersun A, et al. Deep learning on longitudinal CT scans: automated prediction of treatment outcomes in hospitalized tuberculosis patients. iScience, 2023, 26(11):108326. doi:10.1016/j.isci.2023.108326.
[59]	Li Y, Wang B, Wen L, et al. Machine learning and radiomics for the prediction of multidrug resistance in cavitary pulmonary tuberculosis: a multicentre study. Eur Radiol, 2023, 33(1):391-400. doi:10.1007/s00330-022-08997-9.
[60]	秦李祎, 吕平欣, 郭琳, 等. 基于CT图像的肺结核病灶治愈状态判定深度学习模型的建立. 中国防痨杂志, 2024, 46(3):272-278. doi:10.19982/j.issn.1000-6621.20230457.
[61]	Zhang J, Huang T, He X, et al. Machine learning-based model assists in differentiating Mycobacterium avium complex pulmonary disease from pulmonary tuberculosis: a multicenter study[J/OL]. J Imaging Inform Med, (2025-04-01)[2025-05-01]. https://link.springer.com/article/10.1007/s10278-025-01486-7. doi:10.1007/s10278-025-01486-7.
[62]	张嘉诚, 黄婷婷, 何旭, 等. 基于CT特征和机器学习的鸟-胞内分枝杆菌复合群肺病和初治肺结核鉴别诊断模型的构建与验证. 中国医学影像学杂志, 2024, 32(10):1007-1013,1039. doi:10.3969/j.issn.1005-5185.2024.10.007.
[63]	Zhang K, Qi S, Cai J, et al. Content-based image retrieval with a Convolutional Siamese Neural Network: Distinguishing lung cancer and tuberculosis in CT images. Comput Biol Med, 2022, 140:105096. doi:10.1016/j.compbiomed.2021.105096.

证据质量分级	具体描述	表达字母
高	非常确信真实的效应值接近效应估计,未来研究几乎不可能改变现有评价结果的可信度	A
中	对效应估计值有中等程度的信心:真实值有可能接近估计值,但仍存在二者大小相同的可能性;未来研究可能对现有评估有重要影响,可能改变评价结果的可信度	B
低	对效应估计值的确信程度有限:真实值可能与估计值大不相同;未来研究很有可能对现有评估有重要影响,改变评估结果可信度的可能性较大	C
极低	对效应估计值的确信程度有限:真实值可能与估计值大不相同;未来研究很有可能对现有评估有重要影响,改变评估结果可信度的可能性较大	D

推荐强度分级	具体描述	表达数字
强烈推荐	明确显示所推荐的干预措施利大于弊或弊大于利	1
有条件推荐	已有证据显示利弊不确定或无论质量高低的证据显示利弊相当	2