胸部影像联合人工智能用于肺结核规范化筛查:实施瓶颈与优化策略

doi:10.19982/j.issn.1000-6621.20260421

中国防痨杂志 ›› 2026, Vol. 48 ›› Issue (10): 1471-1479.doi: 10.19982/j.issn.1000-6621.20260421

胸部影像联合人工智能用于肺结核规范化筛查:实施瓶颈与优化策略

刘振国¹, 邢妩², 凌杰³, 姚山虎⁴, 白丽琼⁵, 容鹏飞⁴()

¹ 中南大学湘雅三医院感染科, 长沙 410013
² 中南大学湘雅医院放射科, 长沙 410008
³ 湖南省结核病防治所(湖南省胸科医院)放射科, 长沙 410013
⁴ 中南大学湘雅三医院放射科, 长沙 410013
⁵ 湖南省结核病防治所(湖南省胸科医院)办公室, 长沙 410013

收稿日期:2026-07-23 出版日期:2026-10-10 发布日期:2026-09-30
通信作者: 容鹏飞,Email:rongpengfei66@163.com
基金资助:
湖南省重点研发计划项目(2026AQ2007)

Chest imaging combined with artificial intelligence for standardized tuberculosis screening: implementation bottlenecks and optimization strategies

Liu Zhenguo¹, Xing Wu², Ling Jie³, Yao Shanhu⁴, Bai Liqiong⁵, Rong Pengfei⁴()

¹ Department of Infectious Diseases, The Third Xiangya Hospital of Central South University, Changsha 410013, China
² Department of Radiology, Xiangya Hospital, Central South University, Changsha 410008, China
³ Department of Radiology, Hunan Institute for Tuberculosis Control (Hunan Chest Hospital), Changsha 410013, China
⁴ Department of Radiology, The Third Xiangya Hospital, Central South University, Changsha 410013, China
⁵ Office of Hunan Institute for Tuberculosis Control (Hunan Chest Hospital), Changsha 410013, China

Received:2026-07-23 Online:2026-10-10 Published:2026-09-30
Contact: Rong Pengfei, Email: rongpengfei66@163.com
Supported by:
Hunan Provincial Key Research and Development Program(2026AQ2007)

摘要/Abstract

摘要：

主动筛查是全球范围内结核病防控的核心干预手段,胸部X线(chest radiography,CXR)为无症状人群筛查首选影像工具。当前,我国已构建 “被动因症就诊+社区主动筛查” 双轨并行的病例发现体系,在此基础上,行业共识进一步提出,推动胸部影像+人工智能计算机辅助检测(artificial intelligence-based computer-aided detection, AI-CAD)下沉基层并覆盖高危人群,是提升病例发现效率的核心路径。然而,现有研究多聚焦于AI模型的诊断效能验证,尚缺乏适配我国中低结核病流行背景的分层筛查标准、标准化全流程方案、系统的卫生经济学评价及覆盖的质量控制体系。依据世界卫生组织(World Health Organization,WHO)及我国现行结核病防控指南,本文首先系统梳理CXR在肺结核筛查中的政策定位,并分层划定适宜AI筛查的目标人群及分级影像设备配置要求;继而围绕“移动数字化X线摄影(digital radiography,DR)+AI”基层筛查模式,深入剖析人群适配性、流程设计、成本效益、模型泛化能力及质控体系五大落地瓶颈;最后,从标准化多源影像数据库建设、分层阶梯式筛查算法优化、一体化全流程质控机制构建、多病种联合筛查模式探索及本土化真实世界队列评估等5个维度,提出切实可行的优化策略。笔者旨在为构建“社区初筛-AI风险分流-病原学确诊-全程随访管理”的肺结核闭环防控体系提供系统性循证支撑。

关键词: 结核, 肺, 体层摄影术, X线计算机, 人工智能, 主动筛查, 成本及成本分析

Abstract:

Active case finding remains a cornerstone of global tuberculosis (TB) control, and chest radiography (CXR) is the primary imaging tool recommended for screening asymptomatic populations. In China, a dual-track case-finding system combining passive case finding among symptomatic individuals and communitybased active screening has been established. Building on this framework, expert consensus recommends the deployment of chest imaging combined with artificial intelligence-based computer-aided detection (AI-CAD) at primary care facilities, targeting highrisk groups to improve case-finding efficiency. However, existing studies have largely focused on validating the diagnostic performance of AI models, while critical gaps remain in the development of stratified screening standards tailored to China’s lowtomoderate TB burden setting, standardized endtoend workflows, systematic cost-effectiveness evaluations, and comprehensive quality assurance systems. Based on current World Health Organization (WHO) recommendations and national TB control guidelines, this commentary first clarifies the policy role of CXR in TB screening and proposes a stratified framework defining appropriate populations for AIassisted screening and tiered requirements for imaging equipment deployment. We then focus on the “mobile digital radiography (DR)-based screening combined with AI” model in primary care settings and analyze five major implementation challenges: population applicability, workflow optimization, costeffectiveness, model generalizability, and quality assurance. To address these challenges, we propose actionable strategies across five dimensions: (1)establishing standardized multisource imaging databases; (2)developing stratified and stepwise screening strategies and algorithms; (3)constructing integrated, end-to-end quality assurance mechanisms; (4)exploring multidisease integrated screening approaches; (5)conducting localized, realworld cohort evaluations. These efforts aim to provide systematic evidencebased support for establishing a closedloop TB prevention and control system integrating communitybased initial screening, AIdriven risk stratification, etiological confirmation, and longitudinal followup management.

Key words: Tuberculosis, pulmonary, Tomography, X-ray computed, Artificial intelligence, Active screening, Costs and cost analysis

中图分类号:

R521
R81

刘振国, 邢妩, 凌杰, 姚山虎, 白丽琼, 容鹏飞. 胸部影像联合人工智能用于肺结核规范化筛查:实施瓶颈与优化策略[J]. 中国防痨杂志, 2026, 48(10): 1471-1479. doi: 10.19982/j.issn.1000-6621.20260421

Liu Zhenguo, Xing Wu, Ling Jie, Yao Shanhu, Bai Liqiong, Rong Pengfei. Chest imaging combined with artificial intelligence for standardized tuberculosis screening: implementation bottlenecks and optimization strategies[J]. Chinese Journal of Antituberculosis, 2026, 48(10): 1471-1479. doi: 10.19982/j.issn.1000-6621.20260421

图/表 1

参考文献 55

[1]	World Health Organization. WHO consolidated guidelines on tuberculosis. Module 2: screening—systematic screening for tuberculosis disease[R]. Geneva: World Health Organization, 2021.
[2]	World Health Organization. Use of computer-aided detection software for tuberculosis screening: WHO policy statement[R]. Geneva: World Health Organization, 2025.
[3]	屈燕, 李涛, 马文斌, 等. 世界卫生组织《2025年全球结核病报告》解读[J]. 结核与肺部疾病杂志, 2025, 6(6): 613-623. doi:10.19983/j.issn.2096-8493.20250178.
[4]	Wykowski J H, Phillips C, Ngo T, et al. A systematic review of potential screening biomarkers for active TB disease[J]. J Clin Tuberc Other Mycobact Dis, 2021, 25: 100284. doi:10.1016/j.jctube.2021.100284.
[5]	中国防痨协会结核病控制专业分会, 中国防痨协会老年结核病防治专业分会, 《中国防痨杂志》编辑委员会. 中国社区肺结核主动筛查循证指南[J]. 中国防痨杂志, 2022, 44(10): 987-997. doi:10.19982/j.issn.1000-6621.20220321.
[6]	中国防痨协会影像专业分会, 中华医学会结核病学分会, 中国防痨协会标准化专业分会, 等. 胸部影像学检查人工智能辅助读片技术在肺结核患者发现中的应用专家共识[J]. 中国防痨杂志, 2025, 47(9): 1093-1104. doi:10.19982/j.issn.1000-6621.20250234.
[7]	Suchal Z A, Ain N U, Rehman A, et al. X-rays in the AI age: revolutionizing pulmonary tuberculosis diagnosis—a systematic review & meta-analysis[J]. J Med Artif Intell, 2025, 8: 36-53. doi:10.21037/jmai-24-363.
[8]	Munjal P, Mahrooqi A A, Rajan R, et al. Population-scale cross-sectional observational study for AI-powered TB screening on one million CXRs[J]. NPJ Digit Med, 2025, 8(1): 418. doi:10.1038/s41746-025-01832-7. pmid: 40634545
[9]	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[J]. 中国防痨杂志, 2024, 46(2): 127-140. doi:10.19982/j.issn.1000-6621.20230428.
[10]	Emery J C, Dodd P J, Banu S, et al. Estimating the contribution of subclinical tuberculosis disease to transmission: An individual patient data analysis from prevalence surveys[J]. Elife, 2023, 12: e82469. doi:10.7554/eLife.82469.
[11]	Akalu T Y, Clements A C A, Wolde H F, et al. Economic burden of multidrug-resistant tuberculosis on patients and households: a global systematic review and meta-analysis[J]. Sci Rep, 2023, 13(1): 22361. doi:10.1038/s41598-023-47094-9.
[12]	Mungai B, Ong’angò J, Ku C C, et al. Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey[J]. PLOS Glob Public Health, 2022, 2(11): e0001272. doi:10.1371/journal.pgph.0001272.
[13]	Ehrlich R, Barker S, Te Water Naude J, et al. Accuracy of Computer-Aided Detection of Occupational Lung Disease: Silicosis and Pulmonary Tuberculosis in Ex-Miners from the South African Gold Mines[J]. Int J Environ Res Public Health, 2022, 19(19):12402. doi:10.3390/ijerph191912402.
[14]	Macpherson L, Kik S V, Quartagno M, et al. Diagnostic Accuracy of Chest X-ray Computer-Aided Detection Software for Detection of Prevalent and Incident Tuberculosis in Household Contacts[J]. Clin Infect Dis, 2025, 80(3): 626-636. doi:10.1093/cid/ciae528.
[15]	Qin Z Z, Ahmed S, Sarker M S, et al. Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms[J]. Lancet Digit Health, 2021, 3(9): e543-e554. doi:10.1016/S2589-7500(21)00116-3.
[16]	de Nooy A, Miller C, Ockhuisen T, et al. Guiding the development of the tuberculosis screening target product profile using single-screen and multi-screen approaches: a modelling study[J]. Lancet Glob Health, 2025, 13(10): e1750-e1760. doi:10.1016/S2214-109X(25)00244-X. pmid: 40975082
[17]	Shukla R. AI X-ray for tuberculosis screening in remote Nepal: Benefits and challenges from a doctor’s perspective[J]. J Public Health Res, 2025, 14(4): 22799036251399279. doi:10.1177/22799036251399279.
[18]	Garg T, John S, Abdulkarim S, et al. Implementation costs and cost-effectiveness of ultraportable chest X-ray with artificial intelligence in active case finding for tuberculosis in Nigeria[J]. PLOS Digit Health, 2025, 4(6):e0000894. doi:10.1371/journal.pdig.0000894.
[19]	Wei X, Liang D, Zhang Z, et al. Active case finding using mobile vans with artificial intelligence aided radiology tests and sputum collection for rapid diagnostic tests to reduce tuberculosis prevalence among high-risk population in rural China: Protocol for a pragmatic trial[J]. PLoS One, 2025, 20(4): e0316073. doi:10.1371/journal.pone.0316073.
[20]	Jiang W, Zhang H, Li Z, et al. AI-Powered Chest X-Ray for Diagnosing Pulmonary Tuberculosis in County and Township Health Care Facilities in Yichang: Retrospective, Real-World Study[J]. J Med Internet Res, 2025, 27: e83041. doi:10.2196/83041.
[21]	Wong A, Lee J R H, Rahmat-Khah H, et al. TB-Net: A Tailored, Self-Attention Deep Convolutional Neural Network Design for Detection of Tuberculosis Cases From Chest X-Ray Images[J]. Front Artif Intell, 2022, 5: 827299. doi:10.3389/frai.2022.827299.
[22]	Nsengiyumva N P, Hussain H, Oxlade O, et al. Triage of Persons With Tuberculosis Symptoms Using Artificial Intelligence-Based Chest Radiograph Interpretation: A Cost-Effectiveness Analysis[J]. Open Forum Infect Dis, 2021, 8(12): ofab567. doi:10.1093/ofid/ofab567.
[23]	Wei Y, Cui X, Chong L, et al. Validating the effectiveness of an AI algorithm for pulmonary tuberculosis screening using chest X-ray: Retrospective study and test accuracy with localizer images of the chest CT[J]. PLoS One, 2026, 21(2): e0338810. doi:10.1371/journal.pone.0338810.
[24]	中华医学会放射学分会传染病放射学专业委员会. 肺结核影像学及分级诊断专家共识[J]. 新发传染病电子杂志, 2018, 3(2): 118-127. doi:10.3877/j.issn.2096-2738.2018.02.017.
[25]	张嘉诚, 唐神结, 侯代伦, 等. 胸部CT联合人工智能辅助检测在肺结核诊疗中的研究进展[J]. 结核与肺部疾病杂志, 2026, 7(1): 112-119. doi:10.19983/j.issn.2096-8493.20250134.
[26]	Wang Q, Zhang Z, Xia L, et al. Using AI system to detect active tuberculosis in a high-prevalence setting on CT scans: a multi-center study[J]. Sci Rep, 2025, 15(1): 39546. doi:10.1038/s41598-025-23172-y.
[27]	World Health Organization. Target product profiles for tuberculosis screening tests[R]. Geneva: World Health Organization, 2025.
[28]	丁峰, 卢水华. 《世界卫生组织结核病综合指南模块3:诊断》第四版解读[J]. 结核与肺部疾病杂志, 2025, 6(6): 624-633. doi:10.19983/j.issn.2096-8493.20250072.
[29]	中华医学会, 中华医学会杂志社, 中华医学会全科医学分会, 等. 肺结核基层诊疗指南(2018年)[J]. 中华全科医师杂志, 2019, 18(8): 709-717. doi:10.3760/cma.j.issn.1671-7368.2019.08.002.
[30]	深圳新闻网. 龙华区慢性病防治中心党总支创新方式方法为终结结核病贡献力量[EB/OL]. [2026-07-20]. https://www.sznews.com/news/content/2021-04/20/content_24145571.htm.
[31]	深圳市第三人民医院. 深圳市第三人民医院医学人工智能应用案例入选首届全国医学人工智能大会典型案例[EB/OL]. [2026-07-20]. http://www.szsdsrmyy.com/ylfw/yldt/content/post_1615216.html.
[32]	深圳市南山区慢性病防治院. 南山区创新开展社区XP筛查项目助力打造“无结核城区”[EB/OL]. [2026-07-20]. https://www.sznsmby.cn/Item/4127.aspx.
[33]	Menzies N A, Gomez G B, Bozzani F, et al. Cost-effectiveness and resource implications of aggressive action on tuberculosis in China, India, and South Africa: a combined analysis of nine models[J]. Lancet Glob Health, 2016, 4(11): e816-e826. doi:10.1016/S2214-109X(16)30265-0. pmid: 27720689
[34]	Alsdurf H, Empringham B, Miller C, et al. Tuberculosis screening costs and cost-effectiveness in high-risk groups: a systematic review[J]. BMC Infect Dis, 2021, 21(1): 935. doi:10.1186/s12879-021-06633-3. pmid: 34496804
[35]	国务院办公厅. 国务院办公厅关于建立健全基层医疗卫生机构补偿机制的意见[Z]. 国办发〔2010〕62号. 2010-12-10.
[36]	财政部, 国家卫生健康委, 国家医保局, 等. 财政部国家卫生健康委国家医保局国家中医药局国家疾控局关于印发基本公共卫生服务等5项补助资金管理办法的通知[Z].财社〔2024〕56号. 2024-05-21.
[37]	国家卫生健康委, 财政部, 国家中医药局, 等. 关于做好2025年基本公共卫生服务工作的通知[Z]. 国卫基层发〔2025〕7号. 2025-06-23.
[38]	浙江省疾病预防控制中心结核病防治所. 我省人工智能赋能无结核城市建设案例入选第78届世界卫生大会边会展示[EB/OL]. [2026-07-20]. https://www.cdc.zj.cn/ywpd/jhbyfkz/ywdt/202505/t20250522_21810.shtml.
[39]	王炜丽. “一扫双筛”半年免费筛查超4万人[N/OL]. 湖州日报, 2026-07-13. [2026-07-20]. https://szb.hz66.com/hzrb/html/2026-07/13/content_117511_19697209.htm.
[40]	Worodria W, Castro R, Kik S V, et al. A multi-country head-to-head accuracy comparison of automated chest X-ray algorithms for tuberculosis[J]. Ann Am Thorac Soc, 2026, 23(5): 728-736. doi:10.1093/annalsats/aaoag011.
[41]	新华网. 影像上云、AI初筛重庆基层结核病防控迎来“智能升级”[EB/OL]. [2026-07-20]. http://www.cq.xinhuanet.com/20250905/cacb220e16a940a9808430853eed1841/c.html.
[42]	喻芳, 易红. 重庆:“影像云+AI”助结核病防控提速[EB/OL]. [2026-07-20]. https://www.jkb.com.cn/news/industryNews/2025/1118/507133.html.
[43]	陈伟, 孙慧娟, 赵雁林. 新时期我国结核病防治服务体系建设及展望[J]. 结核与肺部疾病杂志, 2024, 5(2): 95-100. doi:10.19983/j.issn.2096-8493.2024025.
[44]	德清新闻网. 推进“无结核县”建设向终结结核流行目标全速迈进[EB/OL]. [2026-07-20]. https://dqnews.zjol.com.cn/dqnews/system/2023/12/07/034464257.shtml.
[45]	湖州市卫生健康委员会. 德清“三个到位”高品质推进“无结核县”建设[EB/OL].[2026-07-20]. http://wjw.huzhou.gov.cn/art/2023/10/27/art_1229602483_58899174.html.
[46]	德清新闻网. 我县探索“无结核城市”新路径[EB/OL]. [2026-07-20]. https://dqnews.zjol.com.cn/dqnews/system/2025/10/22/035076399.shtml.
[47]	郑平明, 金玫华, 丁忠明, 等. 浙江省湖州市“无结核城市”建设实践与思考[J]. 中国防痨杂志, 2024, 46(10): 1193-1197. doi:10.19982/j.issn.1000-6621.20240142.
[48]	Sathitratanacheewin S, Sunanta P, Pongpirul K. Deep learning for automated classification of tuberculosis-related chest X-Ray: dataset distribution shift limits diagnostic performance genera-lizability[J]. Heliyon, 2020, 6(8): e04614. doi:10.1016/j.heliyon.2020.e04614.
[49]	Wu E, Wu K, Daneshjou R, et al. How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals[J]. Nat Med, 2021, 27(4): 582-584. doi:10.1038/s41591-021-01312-x. pmid: 33820998
[50]	Sebastian J, Olaru I D, Giannakis A, et al. Detection of other pathologies when utilising computer-assisted digital solutions for TB screening[J]. IJTLD Open, 2024, 1(12): 533-539. doi:10.5588/ijtldopen.24.0428. pmid: 39679206
[51]	央视网. 浙江湖州“一扫双筛”三年行动将惠及20万人[EB/OL]. [2026-07-20]. https://city.news.cctv.com/2025/08/20/ARTIBBRpFcMcfLJydmKzllqB250820.shtml.
[52]	Azman A S, Golub J E, Dowdy D W. How much is tuberculosis screening worth? Estimating the value of active case finding for tuberculosis in South Africa, China, and India[J]. BMC Med, 2014, 12: 216. doi:10.1186/s12916-014-0216-0. pmid: 25358459
[53]	深圳新闻网. 结核病综合防治系统加入“扶贫事业” 南山将“全国典型”推广到四省五县[EB/OL]. [2026-07-20]. https://www.sznews.com/news/content/2021-06/15/content_24297617.htm
[54]	黄垚, 范玉铮, 王翔宇, 等. 2011—2020年深圳市南山区肺结核患者管理和治疗效果分析[J]. 结核与肺部疾病杂志, 2022, 3(6):463-468. doi:10.19983/j.issn.2096-8493.20220098.
[55]	深圳新闻网. 南山“三个创新”为结核病防控提质增效 5年来流动人口发病率年均递降9.4%[EB/OL]. [2026-07-20]. https://inanshan.sznews.com/content/2021-07/23/content_24417918.htm.

胸部影像联合人工智能用于肺结核规范化筛查:实施瓶颈与优化策略

Chest imaging combined with artificial intelligence for standardized tuberculosis screening: implementation bottlenecks and optimization strategies

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 1

参考文献 55

相关文章 15

编辑推荐

Metrics

本文评价

[1]	许超艳, 韦姣姣, 李姗姗, 姚琳, 李凌, 高孟秋. 胞内分枝杆菌肺病早期诊断模型构建及临床评价[J]. 中国防痨杂志, 2026, 48(9): 1290-1299.
[2]	郭晓雯, 焦天宇, 孙丽, 倪聪慧, 王梓霖, 王昊. 基于CE-T₁WI影像组学的机器学习模型鉴别结核性与布鲁氏菌性脊柱炎的多中心研究[J]. 中国防痨杂志, 2026, 48(8): 1184-1191.
[3]	孙郑, 刘炯雅, 陈驰, 于全骥, 李亚男, 陈诚, 竺丽梅. 人工智能辅助CT阅片系统在综合医院肺结核早发现中的应用[J]. 中国防痨杂志, 2026, 48(5): 586-593.
[4]	唐顺定, 许琳, 李玲, 寸得娇, 杨蕊. 云南省民族地区≥65岁老年人接受肺结核主动筛查的意愿及影响因素分析[J]. 中国防痨杂志, 2026, 48(1): 49-56.
[5]	中国防痨协会影像专业分会, 中华医学会结核病学分会, 中国防痨协会标准化专业分会, 中国防痨协会结核病控制专业分会. 胸部影像学检查人工智能辅助读片技术在肺结核患者发现中的应用专家共识[J]. 中国防痨杂志, 2025, 47(9): 1093-1104.
[6]	阿布都热苏力·吐尔孙, 阿布都克尤木江·阿布力孜, 帕提曼·买买提, 黄陈翠, 沈玲燕, 马依迪丽·尼加提. 基于纵向胸部CT的影像组学深度学习预测肺结核患者疗效的研究[J]. 中国防痨杂志, 2025, 47(8): 1044-1052.
[7]	焦家欢, 孙长峰, 吴刚, 黄富礼, 盛云建. 基于机器学习算法的诊断模型对结核性胸腔积液的应用价值[J]. 中国防痨杂志, 2025, 47(8): 1053-1061.
[8]	朱庆东, 赵春艳, 谢周华, 宋树林, 宋畅. 基于人工智能的CT影像组学在结核病诊断和治疗反应监测中应用的研究进展[J]. 中国防痨杂志, 2025, 47(8): 1068-1076.
[9]	李婷婷, 刘欢庆, 雷倩, 尤著宏, 赵国连. 基于机器学习算法的诊断模型对结核性胸膜炎的应用价值[J]. 中国防痨杂志, 2025, 47(11): 1508-1514.
[10]	李汶翰, 杨静, 李春华. 人工智能在肺结核影像诊断及耐药性预测中的研究进展[J]. 中国防痨杂志, 2024, 46(9): 1098-1103.
[11]	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[J]. 中国防痨杂志, 2024, 46(3): 253-259.
[12]	秦李祎, 吕平欣, 郭琳, 钱令军, 肖谦, 杨阳, 尚园园, 贾俊楠, 初乃惠, 刘远明, 李卫民. 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[J]. 中国防痨杂志, 2024, 46(3): 272-278.
[13]	刘雪艳, 王芳, 李春华, 唐光孝, 郑娇凤, 王惠秋, 李玉蕊, 王佳男, 舒伟强, 吕圣秀. 基于深度学习的继发性肺结核CT辅助诊断模型构建及验证[J]. 中国防痨杂志, 2024, 46(3): 279-287.
[14]	高珊, 聂文娟, 侯代伦, 初乃惠. 非结核分枝杆菌肺病影像学表现及应用人工智能新技术的研究进展[J]. 中国防痨杂志, 2024, 46(3): 362-366.
[15]	李文婷, 王丽, 方勇, 顾瑾, 沙巍. 基于CT影像的深度学习模型在肺结核与非结核分枝杆菌肺病中的鉴别诊断价值[J]. 中国防痨杂志, 2024, 46(10): 1236-1242.