肺结核X线胸片智能辅助诊断系统在基层医院的临床效能评价

doi:10.19983/j.issn.2096-8493.20210129

结核与肺部疾病杂志 ›› 2022, Vol. 3 ›› Issue (2): 96-101.doi: 10.19983/j.issn.2096-8493.20210129

肺结核X线胸片智能辅助诊断系统在基层医院的临床效能评价

张修磊¹, 王倩¹, 夏丽², 刘远明², 郝焱³, 郭琳²()

¹山东省公共卫生临床中心预防控制处, 济南 250101
²深圳市智影医疗科技有限公司,深圳 518109
³石溪大学神经生物和行为学系, 美国纽约 NY11794

收稿日期:2021-10-11 出版日期:2022-06-30 发布日期:2022-04-18
通信作者: 郭琳 E-mail:guolin913@outlook.com
基金资助:
国家重点研发计划(2019YFE0121400);山东省医药卫生科技发展计划项目(2019WS533);深圳市科技计划(KQTD2017033110081833);深圳市科技计划(JSGG20201102162802008);深圳市基础研究资助项目(JCYJ20190813153413160);山东省人文社会科学课题(2021-ZXJK-16)

Clinical evaluation of chest X-radiograph computer aided diagnostic system for pulmonary tuberculosis applied in primary hospitals

ZHANG Xiu-lei¹, WANG Qian¹, XIA Li², LIU Yuan-Ming², HAO Yan³, GUO Lin²()

¹Department of Prevention and Control, Shandong Provincial Public Health Clinical Center, Ji’nan, China
²Shenzhen Smart Imaging Healthcare Co., Ltd, Shenzhen, 518109 China
³Stony Brook University, Department of Neurobiology and Behavior, New York NY11794, USA

Received:2021-10-11 Online:2022-06-30 Published:2022-04-18
Contact: GUO Lin E-mail:guolin913@outlook.com
Supported by:
National Key R&D Program of China(2019YFE0121400);Shandong Province Medicine and Health Science and Technology Development Plan Project(2019WS533);Shenzhen Science and Technology Program(KQTD2017033110081833);Shenzhen Science and Technology Program(JSGG20201102162802008);Shenzhen Fundamental Research Program(JCYJ20190813153413160);Shandong Provincial Humanities and Social Science Project(2021-ZXJK-16)

摘要/Abstract

摘要：

目的: 评价人工智能(AI)辅助诊断系统在基层结核病防治机构中的临床应用价值,为AI系统在基层的实际应用提供依据。方法: 回顾性纳入了2020年11月至2021年4月山东省8家独立结核病防治所(简称“结防所”)的396例初诊疑似肺结核的患者,通过比较AI系统与结防所医生的阅片结果,分析AI系统在基层医疗机构的临床诊断效能。结果: 396例患者中,AI系统对肺结核的检出率[97.8%(131/134)]高于当地医生 [75.4%(101/134)](χ²=28.88, P<0.05)。AI系统与结防所医生阅片结果一致率为86.1%(341/396),假阳性率分别为0.8%(2/260)和6.5% (17/260)。AI系统诊断的敏感度、特异度、阳性预测值、阴性预测值以及诊断准确率分别为97.8% (95%CI:93.3%~99.5%)、99.2% (95%CI:97.1%~99.9%)、98.5% (95%CI:94.3%~99.9%)、98.6% (95%CI:96.5%~99.8%)和98.7% (95%CI:97.0%~99.6%)。结防所医生的敏感度、特异度、阳性预测值、阴性预测值以及诊断准确率分别为75.4% (95%CI:67.4%~81.9%)、93.5% (95%CI:89.8%~96.0%)、85.6% (95%CI:78.0%~90.9%)、88.1% (95%CI:83.8%~91.5%)和87.4% (95%CI:83.7%~90.3%)。结论: AI辅助诊断系统能够帮助基层医生提高诊断效率和准确率。

关键词: 结核, 肺, 放射摄影术, 人工智能, 方案评价

Abstract: Objective: To evaluate the clinical performance of using artificial intelligence (AI) based computer aided diagnostic (CAD) system on detecting pulmonary tuberculosis (TB) in primary tuberculosis control and prevention facilities.Methods: A retrospective study enrolling 396 untreated presumptive tuberculosis cases was conducted from November 2020 to April 2021 in 8 TB dispensaries in Shandong province, and the clinical performance of the AI system was analyzed by making a comparison between the results from the AI system and from local radiologists.Results: The TB detection rate of AI system on 396 presumptive cases was higher than that of local radiologists (97.8% (131/134)) vs (75.4% (101/134))(χ²=28.88, P<0.05). The consistency between the AI system and local radiologists was 86.1% (341/396), and the false positive rates of the AI system and local radiologists were 0.8% (2/260) and 6.5% (17/260), respectively. In general, the sensitivity, specificity, positive predictive value, negative predictive value, and the accuracy of the AI system were 97.8% (95%CI: 93.3%-99.5%), 99.2% (95%CI: 97.1%-99.9%), 98.5% (95%CI: 94.3%-99.9%), 98.6% (95%CI: 96.5%-99.8%) and 98.7% (95%CI: 97.0%-99.6%). The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of local radiologists were 75.4% (95%CI: 67.4%-81.9%), 93.5% (95%CI: 89.8%-96.0%), 85.6% (95%CI: 78.0%-90.9%), 88.1% (95%CI: 83.8%-91.5%) and 87.4% (95%CI: 83.7%-90.3%).Conclusion: The AI system could help local radiologists in primary facilities improve diagnostic efficiency and accuracy.

Key words: Tuberculosis, Pulmonary, Radiography, Artificial intelligence, Program evaluation

中图分类号:

R81
R521

张修磊, 王倩, 夏丽, 刘远明, 郝焱, 郭琳. 肺结核X线胸片智能辅助诊断系统在基层医院的临床效能评价[J]. 结核与肺部疾病杂志, 2022, 3(2): 96-101. doi: 10.19983/j.issn.2096-8493.20210129

ZHANG Xiu-lei, WANG Qian, XIA Li, LIU Yuan-Ming, HAO Yan, GUO Lin. Clinical evaluation of chest X-radiograph computer aided diagnostic system for pulmonary tuberculosis applied in primary hospitals[J]. Journal of Tuberculosis and Lung Disease, 2022, 3(2): 96-101. doi: 10.19983/j.issn.2096-8493.20210129

图/表 5

表1

表2

表3

图1~图3

表4

参考文献 20

[1]	World Health Organization. Global tuberculosis report 2019. Geneva: World Health Organization, 2019.
[2]	耿青青. 基层结核病痰检现状及应对措施. 疾病监测与控制, 2017, 11(3):217-218. doi: CNKI:SUN:JBJK.0.2017-03-026. doi: CNKI:SUN:JBJK.0.2017-03-026
[3]	周林, 刘二勇, 孟庆琳, 等. 《WS 288—2017肺结核诊断》标准实施后肺结核诊断质量评估分析. 中国防痨杂志, 2020, 42(9):32-37. doi: 10.3969/j.issn.1000-6621.2020.09.005. doi: 10.3969/j.issn.1000-6621.2020.09.005
[4]	林春伟. 基于卷积神经网络的肺结节检测方法研究. 广州: 华南理工大学, 2017.
[5]	Wang J, Ding H, Azamian FM, et al. Detecting Cardiovascular Disease from Mammograms With Deep Learning. IEEE Trans Med Imaging, 2017, 36(5):1172-1181. doi: 10.1109/TMI.2017.2655486. doi: 10.1109/TMI.2017.2655486 URL
[6]	Xiangyu Chen, Yanwu Xu, Damon Wing Kee Wong, et al. Glaucoma detection based on deep convolutional neural network. Annu Int Conf IEEE Eng Med Biol Soc, 2015, 2015:715-718. doi: 10.1109/EMBC.2015.7318462. doi: 10.1109/EMBC.2015.7318462 pmid: 26736362
[7]	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. doi: 10.3233/XST-210894
[8]	刘广天, 刘涛, 王晓炜, 等. 宁夏地区“互联网+医疗”模式在结核病防治工作中的应用. 中国防痨杂志, 2020, 42(7):676-681. doi: 10.3969/j.issn.1000-6621.2020.07.007. doi: 10.3969/j.issn.1000-6621.2020.07.007
[9]	曹盼, 王斐, 刘哲, 等. 特征金字塔网络在胸部X线摄影图像上筛检肺结核的价值. 中国防痨杂志, 2019, 41(3):288-293. doi: 10.3969/j.issn.1000-6621.2019.03.009. doi: 10.3969/j.issn.1000-6621.2019.03.009
[10]	Jin HE, Sunggyun P, Kwang-Nam J, et al. Development and Validation of a Deep Learning-based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs. Clin Infect Dis, 2019, 69(5):739-747. doi: 10.1093/cid/ciy967. doi: 10.1093/cid/ciy967 URL
[11]	Lee JH, Park S, Hwang EJ, et al. Deep learning-based automated detection algorithm for active pulmonary tuberculosis on chest radiographs: diagnostic performance in systematic screening of asymptomatic individuals. Eur Radiol, 2021, 31(2):1069-1080. doi: 10.1007/s00330-020-07219-4. doi: 10.1007/s00330-020-07219-4 URL
[12]	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. doi: 10.1038/s41746-021-00471-y URL
[13]	Luo H, Xu G, Li C, et al. Real-time artificial intelligence for detection of upper gastrointestinal cancer by endoscopy: a multicentre, case-control, diagnostic study. Lancet Oncol, 2019, 20(12):1645-1654. doi: 10.1016/S1470-2045(19)30637-0. doi: 10.1016/S1470-2045(19)30637-0 URL
[14]	Litjens G, Sánchez C, Timofeeva N, et al. Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis. Sci Rep, 2016, 6:26286. doi: 10.1038/srep26286. doi: 10.1038/srep26286 pmid: 27212078
[15]	Mckinney SM, Sieniek M, Godbole V, et al. International evaluation of an AI system for breast cancer screening. Nature, 2020, 577(7788):89-94. doi: 10.1038/s41586-019-1799-6. doi: 10.1038/s41586-019-1799-6 URL
[16]	Liang M, Tang W, Xu DM, et al. Low-Dose CT Screening for Lung Cancer: Computer-aided Detection of Missed Lung Cancers. Radiology, 2016, 281(1):279-288. doi: 10.1148/radiol.2016150063. doi: 10.1148/radiol.2016150063 URL
[17]	Li X, Zhou Y, Du P, et al. A deep learning system that generates quantitative CT reports for diagnosing pulmonary Tuberculosis. Appl Intell, 2021, 51(6):4082-4093. doi: 10.1007/s10489-020-02051-1. doi: 10.1007/s10489-020-02051-1 URL
[18]	李帅. 基于深度学习的胸片辅助诊断算法. 广州: 广东工业大学, 2019.
[19]	张金. 基于深度学习的肺结节识别与检测研究. 重庆: 西南大学, 2018.
[20]	柳馨雨. 基于深度学习的胸片肺结节识别检测研究. 桂林: 桂林电子科技大学, 2019.

专家1	专家2		合计 (例)	Kappa值 (95%CI)	P值
专家1	阳性(例)	阴性(例)	合计 (例)	Kappa值 (95%CI)	P值
阳性	126	3	129	0.95(0.92~0.99)	<0.05
阴性	5	262	267
合计	131	265	396

AI系统筛查结果	结防所诊断小组阅片结果		合计
AI系统筛查结果	肺结核	非肺结核	合计
肺结核	98	35	133
非肺结核	20	243	263
合计	118	278	396

结防所诊断小组与 AI系统阅片结果	高年资专家组阅片结果		合计
结防所诊断小组与 AI系统阅片结果	阳性	阴性	合计
AI系统阳性,医生阴性	33	2	35
AI系统阴性,医生阳性	3	17	20
合计	36	19	55

检测方法	病原学或高年资专家组评估		敏感度 (%)	特异度 (%)	阳性预测值(%)	阴性预测值(%)	诊断准确率(%)
检测方法	阳性(例)	阴性(例)	敏感度 (%)	特异度 (%)	阳性预测值(%)	阴性预测值(%)	诊断准确率(%)
AI系统
阳性	131	2	97.8	99.2	98.5	98.6	98.7
阴性	3	260	(93.3~99.5)	(97.1~99.9)	(94.3~99.9)	(96.5~99.8)	(97.0~99.6)
结防所诊断小组
阳性	101	17	75.4	93.5	85.6	88.1	87.4
阴性	33	245	(67.4~81.9)	(89.8~96.0)	(78.0~90.9)	(83.8~91.5)	(83.7~90.3)

肺结核X线胸片智能辅助诊断系统在基层医院的临床效能评价

Clinical evaluation of chest X-radiograph computer aided diagnostic system for pulmonary tuberculosis applied in primary hospitals

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 20

相关文章 15

编辑推荐

Metrics

本文评价

友情链接

[1]	卢水华. 关注结核病共患病已成为公共卫生的需要[J]. 结核与肺部疾病杂志, 2022, 3(4): 255-260.
[2]	古力米娜·阿布力米提, 麦维兰江·阿不力米提, 地尔木拉提·吐逊, 刘振江, 何懿, 苏伟, 欧喜超. 2021年喀什地区肺结核患者利福平耐药影响因素分析[J]. 结核与肺部疾病杂志, 2022, 3(4): 269-273.
[3]	杨震, 雷囡, 赵飞, 何艳萍, 林娜, 张治国. 北京市昌平区高等院校新生结核分枝杆菌潜伏感染状况调查及潜伏感染者预防性治疗效果分析[J]. 结核与肺部疾病杂志, 2022, 3(4): 274-280.
[4]	董昭良, 姚黎明, 李领娣, 王连波, 姚晓伟, 李卓, 刘丰胜, 贾晨光. 保守方法治疗轻型脊柱结核的临床疗效[J]. 结核与肺部疾病杂志, 2022, 3(4): 281-286.
[5]	李义帅, 秦学博, 李香兰, 魏兰, 段小亮, 张磊, 陈亮, 李建行. 电视辅助胸腔镜手术与开胸手术治疗难治性空洞性肺结核的效果分析[J]. 结核与肺部疾病杂志, 2022, 3(4): 292-295.
[6]	李军霞, 孟艺哲, 张亚楠, 陈颜强, 赵青. 12例结核性神经根脊髓炎的临床特征及磁共振成像特点分析[J]. 结核与肺部疾病杂志, 2022, 3(4): 296-299.
[7]	胡娟, 周燕, 杨澄清. 支气管结核患者焦虑、抑郁心理状况与行电子支气管镜治疗依从性的相关性分析[J]. 结核与肺部疾病杂志, 2022, 3(4): 305-308.
[8]	郦源, 郭茹茹, 吕良敬. 结缔组织病合并结核病的研究进展[J]. 结核与肺部疾病杂志, 2022, 3(4): 309-314.
[9]	钱晓文, 翟晓文. 造血干细胞移植与结核病[J]. 结核与肺部疾病杂志, 2022, 3(4): 315-319.
[10]	张晓林, 李锋. 肺结核致呼吸衰竭研究进展[J]. 结核与肺部疾病杂志, 2022, 3(4): 320-324.
[11]	刘玉坤, 郭智. 慢性髓系白血病与结核病共病研究进展[J]. 结核与肺部疾病杂志, 2022, 3(4): 325-327.
[12]	何燕超, 揭志军. 综合医院活动性肺结核的早期筛查策略[J]. 结核与肺部疾病杂志, 2022, 3(4): 334-337.
[13]	周伊南, 朱惠莉. 慢性阻塞性肺疾病合并肺结核的研究进展[J]. 结核与肺部疾病杂志, 2022, 3(4): 338-342.
[14]	陈木兴, 范欣欣, 陈晓红, 林友飞, 黄明翔, 陈力舟, 吴迪. T淋巴细胞亚群检测在新型冠状病毒肺炎临床应用价值中的研究进展[J]. 结核与肺部疾病杂志, 2022, 3(4): 343-346.
[15]	程娟, 贺晓英, 刘铭辉, 韩守华, 陈磊, 刘光福, 潘兆宝, 严琨. 苏尔加分枝杆菌肺病一例[J]. 结核与肺部疾病杂志, 2022, 3(4): 347-352.