Article(id=1322191080204911180, tenantId=1146029695717560320, journalId=1319373162502258839, issueId=1322191025829953744, articleNumber=null, orderNo=null, doi=10.16016/j.2097-0927.202504117, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1745856000000, receivedDateStr=2025-04-29, revisedDate=1749139200000, revisedDateStr=2025-06-06, acceptedDate=null, acceptedDateStr=null, onlineDate=1793164518643, onlineDateStr=2026-10-28, pubDate=1753804800000, pubDateStr=2025-07-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793164518643, onlineIssueDateStr=2026-10-28, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793164518643, creator=13701087609, updateTime=1793164518643, updator=13701087609, issue=Issue{id=1322191025829953744, tenantId=1146029695717560320, journalId=1319373162502258839, year='2025', volume='47', issue='14', pageStart='1557', pageEnd='1684', issueExtLink='null', onlineDate='null', pubDate='1753804800000', pubDateStr='2025-07-30', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1793164505679, creator='13701087609', updateTime=1793164547848, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1322191202804420934, tenantId=1146029695717560320, journalId=1319373162502258839, issueId=1322191025829953744, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1322191202804420935, tenantId=1146029695717560320, journalId=1319373162502258839, issueId=1322191025829953744, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=1676, endPage=1684, ext={EN=ArticleExt(id=1322191080439792205, articleId=1322191080204911180, tenantId=1146029695717560320, journalId=1319373162502258839, language=EN, title=Predictive performance of CT images-based 3D ResNet18 model for identifying lung tuberculosis drug resistance, columnId=1322190400052380037, journalTitle=Journal of Army Medical University, columnName=Biomedical Engineering, runingTitle=null, highlight=null, articleAbstract=
Objective‍

To develop and validate a deep learning model based on chest CT images to accurately distinguish between drug-resistant (DR-TB) and -sensitive tuberculosis (DS-TB).

Methods‍

A retrospective study was conducted on 722 cases of confirmed secondary tuberculosis admitted in our center from January 2019 to December 2022. According to the results of antimicrobial susceptibility test, they were divided into 357 DS-TB cases and 365 DR-TB cases. Pre-existing U-Net segmentation model was employed to segment the lung parenchyma regions in CT images. The dataset was randomly partitioned into a training set and a testing set in an 8:2 ratio. Six 3D deep learning architectures (3D Swin Transformer, 3D ShuffleNet v2, 3D ViT, 3D MobileNet v2, 3D DenseNet, and 3D ResNet18) were employed to evaluate the discriminative efficiency between DS-TB and DR-TB. Hyperparameters were optimized by five-fold cross-validation on the training set to construct the optimal model. The performance of the constructed model was assessed using area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score. Six radiologists independently evaluated DR-TB identification on the test set, and their performance was compared with the best-performing deep learning model.

Results‍

The AUC value in DR-TB prediction was 0.583, 0.704, 0.698, 0.758, 0.736, and 0.841, respectively, for 3D Swin Transformer, 3D ShuffleNet v2, 3D ViT, 3D MobileNet v2, 3D DenseNet, and 3D ResNet18. The 3D ResNet18 model demonstrated optimal performance, achieving a sensitivity of 0.935 (95%CI: 0.880~0.987), a specificity of 0.642 (95%CI: 0.492~0.757), a PPV of 0.750 (95%CI: 0.663~0.835), an NPV of 0.896 (95%CI: 0.809~0.976), an AUC value of 0.841, and a F1-score of 0.832. The radiologists got a F1-score of 0.571, 0.450, 0.675, 0.623, 0.617 and 0.635, respectively, and the F1-score of the 3D ResNet18 model is all higher than that of the radiologists. The highest-performing radiologist achieved sensitivity, specificity, PPV and NPV of 0.701 (95%CI: 0.605~0.802), 0.567 (95%CI: 0.447~0.684), 0.651 (95%CI: 0.549~0.757), and 0.623 (95%CI: 0.500~0.754), with all these values lower than those of the 3D ResNet18 model (P<0.05). Class activation mapping showed that the 3D ResNet18 model could focus on key lesion areas. The class activation mapping demonstrated that the 3D ResNet18 model could effectively focus on critical lesion regions.

Conclusion‍

Our 3D ResNet18 model shows the best predictive performance in identifying DR-TB, and is expected to assist clinical diagnosis for DR-TB.

, authors=Chunhua LI, Xueyan LIU, Jiaofeng ZHENG, Xiangxin ZENG, Yurui LI, Wenwen LIU, Shengxiu LYU, authorsList=Chunhua LI, Xueyan LIU, Jiaofeng ZHENG, Xiangxin ZENG, Yurui LI, Wenwen LIU, Shengxiu LYU, authorCompany=null, correspAuthors=Shengxiu LYU, authorNote=null, correspAuthorsNote=null, copyrightStatement=© 2025 Journal of Army Medical University, copyrightOwner=Editorial Office of Journal of Army Medical University, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1322191081765192282, articleId=1322191080204911180, tenantId=1146029695717560320, journalId=1319373162502258839, language=CN, title=基于CT影像的3D ResNet18模型在肺结核耐药性识别中的预测性能研究, columnId=1322190400245318023, journalTitle=陆军军医大学学报, columnName=生物医学工程, runingTitle=null, highlight=null, articleAbstract=
目的

通过构建并验证一种基于胸部CT影像的深度学习模型,以正确识别耐药肺结核和药物敏感肺结核。

方法

回顾性纳入重庆市公共卫生医疗救治中心2019年1月至2022年12月诊治的722例继发性肺结核CT影像,根据药物敏感性试验结果,将其分为药物敏感肺结核组和耐药肺结核组,其中药物敏感肺结核357例,耐药肺结核365例。采用U-Net分割模型预先对CT影像的肺实质区域进行分割,然后按8∶2的比例随机划分为训练集和测试集。评估6种三维深度学习网络(3D Swin Transformer、3D ShuffleNet v2、3D ViT、3D MobileNet v2、3D DenseNet及3D ResNet18)对肺结核耐药性的识别性能,在训练集上通过五折交叉验证调整超参数,以构建最优深度学习模型。采用曲线下面积(area under the curve,AUC)、灵敏度、特异度、阳性预测值(positive predictive value,PPV)、阴性预测值(negative predictive value,NPV)以及F1值评价模型性能。由6名放射科医师对测试集CT影像进行耐药性识别,并与性能最优的深度学习模型进行性能比较。

结果

3D Swin Transformer、3D ShuffleNet v2、3D ViT、3D MobileNet v2、3D DenseNet及3D ResNet18预测耐药肺结核的AUC分别为0.583、0.704、0.698、0.758、0.736及0.841,3D ResNet18为性能最优深度学习模型,其灵敏度为0.935(95%CI:0.880~0.987),特异度为0.642(95%CI:0.492~0.757),阳性预测值为0.750(95%CI:0.663~0.835),阴性预测值为0.896(95%CI:0.809~0.976),AUC值为0.841,F1值为0.832。放射科医师F1值分别为0.571、0.450、0.675、0.623、0.617、0.635,3D ResNet18模型F1值均高于放射科医师。识别耐药肺结核结果最优的放射科医师的灵敏度、特异度、阳性预测值、阴性预测值分别为0.701(95%CI:0.605~0.802)、0.567(95%CI:0.447~0.684)、0.651(95%CI:0.549~0.757)、0.623(95%CI:0.500~0.754),其灵敏度、阳性预测值和阴性预测值均低于3D ResNet18模型(P<0.05)。类激活映射图表明3D ResNet18能够关注到关键病变区域。

结论

3D ResNet18 模型在肺结核耐药性识别中预测性能最优,有望辅助临床诊断耐药肺结核。

, authors=李春华, 刘雪艳, 郑娇凤, 曾祥鑫, 李玉蕊, 刘雯雯, 吕圣秀, authorsList=李春华, 刘雪艳, 郑娇凤, 曾祥鑫, 李玉蕊, 刘雯雯, 吕圣秀, authorCompany=null, correspAuthors=吕圣秀, authorNote=null, correspAuthorsNote=
吕圣秀,E-mail:
LYU Shengxiu,E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=6sK2V2Le5WYJhC39yixbxA==, magXml=2HwRN1wnyrxioEZyO9CO8Q==, pdfUrl=null, pdf=uHy9Y6rgBVa70GH4wzECiA==, pdfFileSize=3634684, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=jObQ6Puv9AbpNNo6bk0GEA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=vTVR3JpQWCcPzTAUkNWLPw==, mapNumber=null, fund=null)}, authors=[Author(id=1322191082075570783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191083757486689, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191082075570783, language=EN, stringName=Chunhua LI, firstName=Chunhua, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191083837178466, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191082075570783, language=CN, stringName=李春华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191083916870244, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191084013339238, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191083916870244, language=EN, stringName=Xueyan LIU, firstName=Xueyan, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191084093031015, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191083916870244, language=CN, stringName=刘雪艳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191084181111401, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191084273386091, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084181111401, language=EN, stringName=Jiaofeng ZHENG, firstName=Jiaofeng, middleName=null, lastName=ZHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191084361466476, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084181111401, language=CN, stringName=郑娇凤, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191084445352558, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191084537627248, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084445352558, language=EN, stringName=Xiangxin ZENG, firstName=Xiangxin, middleName=null, lastName=ZENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191084613124721, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084445352558, language=CN, stringName=曾祥鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191084684427891, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191084755731061, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084684427891, language=EN, stringName=Yurui LI, firstName=Yurui, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191084806062710, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084684427891, language=CN, stringName=李玉蕊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191084868977272, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191084952863354, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084868977272, language=EN, stringName=Wenwen LIU, firstName=Wenwen, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191085032555131, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084868977272, language=CN, stringName=刘雯雯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191085099663997, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=r202206@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322191085179355775, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191085099663997, language=EN, stringName=Shengxiu LYU, firstName=Shengxiu, middleName=null, lastName=LYU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191085242270336, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191085099663997, language=CN, stringName=吕圣秀, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])])], keywords=[Keyword(id=1322191085342933633, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, orderNo=1, keyword=deep learning), Keyword(id=1322191085405848194, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, orderNo=2, keyword=tuberculosis), Keyword(id=1322191085485539971, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, orderNo=3, keyword=drug resistance), Keyword(id=1322191085556843140, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, orderNo=4, keyword=drug susceptibility), Keyword(id=1322191085615563397, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, orderNo=1, keyword=深度学习), Keyword(id=1322191085703643782, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, orderNo=2, keyword=肺结核), Keyword(id=1322191085795918471, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, orderNo=3, keyword=耐药性), Keyword(id=1322191085879804552, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, orderNo=4, keyword=药物敏感)], refs=[Reference(id=1322191089440768667, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=World Health Organization, journalName=null, refType=null, unstructuredReference=World Health Organization. Global tuberculosis report 2024[EB/OL]. [2024-10-30].https://publichealthupdate.com/global-tuberculosis-report-2024/., articleTitle=Global tuberculosis report 2024, refAbstract=null), Reference(id=1322191089512071836, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.3390/diagnostics12010188, pmid=null, pmcid=null, year=2022, volume=12, issue=1, pageStart=188, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=KARKI M, KANTIPUDI K, YANG F, journalName=Diagnostics (Basel), refType=null, unstructuredReference=KARKI M,KANTIPUDI K,YANG F,et al. Generalization challenges in drug-resistant tuberculosis detection from chest X-rays[J]. Diagnostics (Basel),2022,12(1):188., articleTitle=Generalization challenges in drug-resistant tuberculosis detection from chest X-rays, refAbstract=null), Reference(id=1322191089612735133, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.2147/IDR.S467971, pmid=null, pmcid=null, year=2024, volume=17, issue=null, pageStart=3737, pageEnd=3749, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=ZOU L P, KANG W L, GUO C H, journalName=Infect Drug Resist, refType=null, unstructuredReference=ZOU L P,KANG W L,GUO C H,et al. Treatment outcomes and associated influencing factors among patients with rifampicin-resistant tuberculosis:a multicenter,retrospective,cohort study in China[J]. Infect Drug Resist,2024,17:3737-3749., articleTitle=Treatment outcomes and associated influencing factors among patients with rifampicin-resistant tuberculosis:a multicenter,retrospective,cohort study in China, refAbstract=null), Reference(id=1322191089700815518, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1016/j.ebiom.2019.04.016, pmid=null, pmcid=null, year=2019, volume=43, issue=null, pageStart=356, pageEnd=369, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=CHEN M L, DODDI A, ROYER J, journalName=EBioMedicine, refType=null, unstructuredReference=CHEN M L,DODDI A,ROYER J,et al. Beyond multidrug resistance:Leveraging rare variants with machine and statistical learning models in Mycobacterium tuberculosis resistance prediction[J]. EBioMedicine,2019,43:356-369., articleTitle=Beyond multidrug resistance:Leveraging rare variants with machine and statistical learning models in Mycobacterium tuberculosis resistance prediction, refAbstract=null), Reference(id=1322191089784701599, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.19871/j.cnki.xfcrbzz.2021.01.015, pmid=null, pmcid=null, year=2021, volume=6, issue=1, pageStart=65, pageEnd=72, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=马璐瑶, 郑秋婷, 陆普选, journalName=新发传染病电子杂志, refType=null, unstructuredReference=马璐瑶,郑秋婷,陆普选,等. 基于文献分析的耐多药肺结核影像学研究进展[J]. 新发传染病电子杂志,2021,6(1):65-72., articleTitle=基于文献分析的耐多药肺结核影像学研究进展, refAbstract=null), Reference(id=1322191089868587680, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.19871/j.cnki.xfcrbzz.2021.01.015, pmid=null, pmcid=null, year=2021, volume=6, issue=1, pageStart=65, pageEnd=72, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=MA L Y, ZHENG Q T, LU P X, journalName=Electron J Emerg Infect Dis, refType=null, unstructuredReference=MA L Y,ZHENG Q T,LU P X,et al. Pulmonary multi-drug resistant tuberculosis:a radiological review[J]. Electron J Emerg Infect Dis,2021,6(1):65-72., articleTitle=Pulmonary multi-drug resistant tuberculosis:a radiological review, refAbstract=null), Reference(id=1322191089948279457, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1007/s00330-020-07024-z, pmid=null, pmcid=null, year=2020, volume=30, issue=12, pageStart=6497, pageEnd=6507, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=FENG B, CHEN X M, CHEN Y H, journalName=Eur Radiol, refType=null, unstructuredReference=FENG B,CHEN X M,CHEN Y H,et al. Solitary solid pulmonary nodules:a CT-based deep learning nomogram helps differentiate tuberculosis granulomas from lung adenocarcinomas[J]. Eur Radiol,2020,30(12):6497-6507., articleTitle=Solitary solid pulmonary nodules:a CT-based deep learning nomogram helps differentiate tuberculosis granulomas from lung adenocarcinomas, refAbstract=null), Reference(id=1322191090023776930, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.3760/cma.j.cn112149-20231023-00309, pmid=null, pmcid=null, year=2024, volume=58, issue=2, pageStart=243, pageEnd=244, url=null, language=null, rfNumber=7, rfOrder=7, authorNames=崔效楠, 叶兆祥, journalName=中华放射学杂志, refType=null, unstructuredReference=崔效楠,叶兆祥. 基于术前CT影像的肺结节病理类型预测模型研究[J]. 中华放射学杂志,2024,58(2):243-244., articleTitle=基于术前CT影像的肺结节病理类型预测模型研究, refAbstract=null), Reference(id=1322191090099274403, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.3760/cma.j.cn112149-20231023-00309, pmid=null, pmcid=null, year=2024, volume=58, issue=2, pageStart=243, pageEnd=244, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=CUI X N, YE Z X, journalName=Chin J Radiol, refType=null, unstructuredReference=CUI X N,YE Z X. Study on prediction model of pathological types of pulmonary nodules based on preoperative CT images[J]. Chin J Radiol,2024,58(2):243-244., articleTitle=Study on prediction model of pathological types of pulmonary nodules based on preoperative CT images, refAbstract=null), Reference(id=1322191090195743396, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1038/s41598-025-93718-7, pmid=null, pmcid=null, year=2025, volume=15, issue=null, pageStart=8724, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=AFTAB J, KHAN M A, ARSHAD S, journalName=Sci Rep, refType=null, unstructuredReference=AFTAB J,KHAN M A,ARSHAD S,et al. Artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self-attention deep neural network architecture[J]. Sci Rep,2025,15:8724., articleTitle=Artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self-attention deep neural network architecture, refAbstract=null), Reference(id=1322191090300600997, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1186/s41747-020-00173-2, pmid=null, pmcid=null, year=2020, volume=4, issue=1, pageStart=50, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=HOFMANNINGER J, PRAYER F, PAN J, journalName=Eur Radiol Exp, refType=null, unstructuredReference=HOFMANNINGER J,PRAYER F,PAN J,et al. Automatic lung segmentation in routine imaging is primarily a data diversity problem,not a methodology problem[J]. Eur Radiol Exp,2020,4(1):50., articleTitle=Automatic lung segmentation in routine imaging is primarily a data diversity problem,not a methodology problem, refAbstract=null), Reference(id=1322191090371904166, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.13491/j.issn.1004-714X.2021.06.018, pmid=null, pmcid=null, year=2021, volume=30, issue=6, pageStart=752, pageEnd=747,756, url=null, language=null, rfNumber=10, rfOrder=11, authorNames=徐辉, 岳保荣, 尉可道, journalName=中国辐射卫生, refType=null, unstructuredReference=徐辉,岳保荣,尉可道,等.《X射线计算机体层摄影装置质量控制检测规范》解读[J]. 中国辐射卫生,2021,30(6):752-747,756., articleTitle=《X射线计算机体层摄影装置质量控制检测规范》解读, refAbstract=null), Reference(id=1322191090443207335, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.13491/j.issn.1004-714X.2021.06.018, pmid=null, pmcid=null, year=2021, volume=30, issue=6, pageStart=752, pageEnd=747,756, url=null, language=null, rfNumber=10, rfOrder=12, authorNames=XU H, YUE B R, WEI K D, journalName=Chin J Radiol Health, refType=null, unstructuredReference=XU H,YUE B R,WEI K D,et al. Interpretation of Specification for testing of quality control in X-ray computed tomography[J].Chin J Radiol Health,2021,30(6):752-747,756., articleTitle=Interpretation of Specification for testing of quality control in X-ray computed tomography, refAbstract=null), Reference(id=1322191090506121896, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.19983/j.issn.2096-8493.2024022, pmid=null, pmcid=null, year=2024, volume=5, issue=4, pageStart=376, pageEnd=378, url=null, language=null, rfNumber=11, rfOrder=13, authorNames=中华人民共和国国家卫生和计划生育委员会, journalName=结核与肺部疾病杂志, refType=null, unstructuredReference=中华人民共和国国家卫生和计划生育委员会. WS 288—2017肺结核诊断[J]. 结核与肺部疾病杂志,2024,5(4):376-378., articleTitle=WS 288—2017肺结核诊断, refAbstract=null), Reference(id=1322191090577425065, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.19983/j.issn.2096-8493.2024022, pmid=null, pmcid=null, year=2024, volume=5, issue=4, pageStart=376, pageEnd=378, url=null, language=null, rfNumber=11, rfOrder=14, authorNames=National Health and Family Planning Commission of the People’s Republic of China, journalName=J Tuberc Lung Dis, refType=null, unstructuredReference=National Health and Family Planning Commission of the People’s Republic of China.WS 288:2017 diagnosis of tuberculosis[J]. J Tuberc Lung Dis,2024,5(4):376-378., articleTitle=WS 288:2017 diagnosis of tuberculosis, refAbstract=null), Reference(id=1322191090636145322, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.19871/j.cnki.xfcrbzz.2023.05.013, pmid=null, pmcid=null, year=2023, volume=8, issue=5, pageStart=63, pageEnd=74, url=null, language=null, rfNumber=12, rfOrder=15, authorNames=中国研究型医院学会感染与炎症放射学专业委员会, 中华医学会放射学分会传染病学组, 中国科技产业化促进会数字健康专业委员会, journalName=新发传染病电子杂志, refType=null, unstructuredReference=中国研究型医院学会感染与炎症放射学专业委员会,中华医学会放射学分会传染病学组,中国科技产业化促进会数字健康专业委员会,等. 耐药肺结核影像学诊断专家共识[J]. 新发传染病电子杂志,2023,8(5):63-74., articleTitle=耐药肺结核影像学诊断专家共识, refAbstract=null), Reference(id=1322191090694865579, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.19871/j.cnki.xfcrbzz.2023.05.013, pmid=null, pmcid=null, year=2023, volume=8, issue=5, pageStart=63, pageEnd=74, url=null, language=null, rfNumber=12, rfOrder=16, authorNames=Professional Committee of Infectious and Inflammatory Radiology of Chinese Research Hospital Association, Radiology Branch of Chinese Medical Association, Group of Infectious Diseases, China Association for the Promotion of Science and Technology Industrialization, Digital Health Professional Committee, journalName=Electron J Emerg Infect Dis, refType=null, unstructuredReference=Professional Committee of Infectious and Inflammatory Radiology of Chinese Research Hospital Association; Radiology Branch of Chinese Medical Association,Group of Infectious Diseases; China Association for the Promotion of Science and Technology Industrialization,Digital Health Professional Committee,et al. Expert consensus on imaging diagnosis of drug-resistant pulmonary tuberculosis[J].Electron J Emerg Infect Dis,2023,8(5):63-74., articleTitle=Expert consensus on imaging diagnosis of drug-resistant pulmonary tuberculosis, refAbstract=null), Reference(id=1322191090761974444, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1148/radiol.212213, pmid=null, pmcid=null, year=2023, volume=306, issue=1, pageStart=124, pageEnd=137, url=null, language=null, rfNumber=13, rfOrder=17, authorNames=KAZEMZADEH S, YU J, JAMSHY S, journalName=Radiology, refType=null, unstructuredReference=KAZEMZADEH S,YU J,JAMSHY S,et al. Deep learning detection of active pulmonary tuberculosis at chest radiography matched the clinical performance of radiologists[J]. Radiology,2023,306(1):124-137., articleTitle=Deep learning detection of active pulmonary tuberculosis at chest radiography matched the clinical performance of radiologists, refAbstract=null), Reference(id=1322191090824889005, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1093/cid/ciy967, pmid=null, pmcid=null, year=2019, volume=69, issue=5, pageStart=739, pageEnd=747, url=null, language=null, rfNumber=14, rfOrder=18, authorNames=HWANG E J, PARK S, JIN K N, journalName=Clin Infect Dis, refType=null, unstructuredReference=HWANG E J,PARK S,JIN K N,et al. Development and validation of a deep learning-based automatic detection algorithm for active pulmonary tuberculosis on chest radiographs[J]. Clin Infect Dis,2019,69(5):739-747., articleTitle=Development and validation of a deep learning-based automatic detection algorithm for active pulmonary tuberculosis on chest radiographs, refAbstract=null), Reference(id=1322191090896192174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1038/s41746-020-00322-2, pmid=null, pmcid=null, year=2020, volume=3, issue=null, pageStart=115, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=19, authorNames=RAJPURKAR P, O’CONNELL C, SCHECHTER A, journalName=NPJ Digit Med, refType=null, unstructuredReference=RAJPURKAR P,O’CONNELL C,SCHECHTER A,et al. CheXaid:deep learning assistance for physician diagnosis of tuberculosis using chest x-rays in patients with HIV[J]. NPJ Digit Med,2020,3:115., articleTitle=CheXaid:deep learning assistance for physician diagnosis of tuberculosis using chest x-rays in patients with HIV, refAbstract=null), Reference(id=1322191090967495343, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1038/s41746-022-00648-z, pmid=null, pmcid=null, year=2022, volume=5, issue=1, pageStart=124, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=20, authorNames=WANG C D, MA J C, ZHANG S, journalName=NPJ Digit Med, refType=null, unstructuredReference=WANG C D,MA J C,ZHANG S,et al. Development and validation of an abnormality-derived deep-learning diagnostic system for major respiratory diseases[J]. NPJ Digit Med,2022,5(1):124., articleTitle=Development and validation of an abnormality-derived deep-learning diagnostic system for major respiratory diseases, refAbstract=null), Reference(id=1322191091042992816, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1016/S2589-7500(21)00116-3, pmid=null, pmcid=null, year=2021, volume=3, issue=9, pageStart=e543, pageEnd=e554, url=null, language=null, rfNumber=17, rfOrder=21, authorNames=QIN Z Z, AHMED S, SARKER M S, journalName=Lancet Digit Health, refType=null, unstructuredReference=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., articleTitle=Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting:an evaluation of five artificial intelligence algorithms, refAbstract=null), Reference(id=1322191092678771377, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.3389/frai.2025.1512910, pmid=null, pmcid=null, year=2025, volume=8, issue=null, pageStart=1512910, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=22, authorNames=DE CAMARGO T F O, RIBEIRO G A S, SILVA M C B DA, journalName=Front Artif Intell, refType=null, unstructuredReference=DE CAMARGO T F O,RIBEIRO G A S,SILVA M C B DA,et al. Clinical validation of an artificial intelligence algorithm for classifying tuberculosis and pulmonary findings in chest radiographs[J]. Front Artif Intell,2025,8:1512910., articleTitle=Clinical validation of an artificial intelligence algorithm for classifying tuberculosis and pulmonary findings in chest radiographs, refAbstract=null), Reference(id=1322191092737491634, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.21037/tlcr-21-971, pmid=null, pmcid=null, year=2021, volume=10, issue=12, pageStart=4574, pageEnd=4586, url=null, language=null, rfNumber=19, rfOrder=23, authorNames=DENG J J, ZHAO M M, LI Q Y, journalName=Transl Lung Cancer Res, refType=null, unstructuredReference=DENG J J,ZHAO M M,LI Q Y,et al. Implementation of artificial intelligence in the histological assessment of pulmonary subsolid nodules[J]. Transl Lung Cancer Res,2021,10(12):4574-4586., articleTitle=Implementation of artificial intelligence in the histological assessment of pulmonary subsolid nodules, refAbstract=null), Reference(id=1322191092800406195, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.21037/qims-23-1097, pmid=null, pmcid=null, year=2023, volume=13, issue=12, pageStart=8641, pageEnd=8656, url=null, language=null, rfNumber=20, rfOrder=24, authorNames=SHI C Z, SHAO Y, SHAN F, journalName=Quant Imaging Med Surg, refType=null, unstructuredReference=SHI C Z,SHAO Y,SHAN F,et al. Development and validation of a deep learning model for multicategory pneumonia classification on chest computed tomography:a multicenter and multireader study[J]. Quant Imaging Med Surg,2023,13(12):8641-8656., articleTitle=Development and validation of a deep learning model for multicategory pneumonia classification on chest computed tomography:a multicenter and multireader study, refAbstract=null), Reference(id=1322191092854932148, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1148/radiol.2021219004, pmid=null, pmcid=null, year=2021, volume=299, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=25, authorNames=BAI H X, WANG R, XIONG Z, journalName=Radiology, refType=null, unstructuredReference=BAI H X,WANG R,XIONG Z,et al. Artificial intelligence augmentation of radiologist performance in distinguishing COVID-19 from pneumonia of other origin at chest CT[J]. Radiology,2021,299(1):E225., articleTitle=Artificial intelligence augmentation of radiologist performance in distinguishing COVID-19 from pneumonia of other origin at chest CT, refAbstract=null), Reference(id=1322191092913652405, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.19982/j.issn.1000-6621.20240263, pmid=null, pmcid=null, year=2024, volume=46, issue=10, pageStart=1236, pageEnd=1242, url=null, language=null, rfNumber=22, rfOrder=26, authorNames=李文婷, 王丽, 方勇, journalName=中国防痨杂志, refType=null, unstructuredReference=李文婷,王丽,方勇,等. 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., articleTitle=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, refAbstract=null), Reference(id=1322191092993344182, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.19982/j.issn.1000-6621.20240263, pmid=null, pmcid=null, year=2024, volume=46, issue=10, pageStart=1236, pageEnd=1242, url=null, language=null, rfNumber=22, rfOrder=27, authorNames=LI W T, WANG L, FANG Y, journalName=Chin J Antituberc, refType=null, unstructuredReference=LI W T,WANG L,FANG Y,et al. The value of CT-based deep learning models in differentiating nontuberculous mycobacterial lung disease from pulmonary tuberculosis[J]. Chin J Antituberc,2024,46(10):1236-1242., articleTitle=The value of CT-based deep learning models in differentiating nontuberculous mycobacterial lung disease from pulmonary tuberculosis, refAbstract=null), Reference(id=1322191093052064439, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.19982/j.issn.1000-6621.20230356, pmid=null, pmcid=null, year=2024, volume=46, issue=3, pageStart=279, pageEnd=287, url=null, language=null, rfNumber=23, rfOrder=28, authorNames=刘雪艳, 王芳, 李春华, journalName=中国防痨杂志, refType=null, unstructuredReference=刘雪艳,王芳,李春华,等. 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., articleTitle=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, refAbstract=null), Reference(id=1322191093114979000, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.19982/j.issn.1000-6621.20230356, pmid=null, pmcid=null, year=2024, volume=46, issue=3, pageStart=279, pageEnd=287, url=null, language=null, rfNumber=23, rfOrder=29, authorNames=LIU X Y, WANG F, LI C H, journalName=Chin J Antituberc, refType=null, unstructuredReference=LIU X Y,WANG F,LI C H,et al. Construction and evaluation of a CT-based deep learning model for the auxiliary diagnosis of secondary tuberculosis[J]. Chin J Antituberc,2024,46(3):279-287., articleTitle=Construction and evaluation of a CT-based deep learning model for the auxiliary diagnosis of secondary tuberculosis, refAbstract=null), Reference(id=1322191093194670777, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=null, pmid=null, pmcid=null, year=2020, volume=42, issue=1, pageStart=38, pageEnd=43, url=null, language=null, rfNumber=24, rfOrder=30, authorNames=杨佳, 吕圣秀, 唐光孝, journalName=中国防痨杂志, refType=null, unstructuredReference=杨佳,吕圣秀,唐光孝,等. 初治与复治耐多药肺结核患者的CT表现分析[J]. 中国防痨杂志,2020,42(1):38-43., articleTitle=初治与复治耐多药肺结核患者的CT表现分析, refAbstract=null), Reference(id=1322191093257585338, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=null, pmid=null, pmcid=null, year=2020, volume=42, issue=1, pageStart=38, pageEnd=43, url=null, language=null, rfNumber=24, rfOrder=31, authorNames=YANG J, LYU S X, TANG G X, journalName=Chin J Antituberc, refType=null, unstructuredReference=YANG J,LYU S X,TANG G X,et al. Analysis of CT findings in patients with initial and retreated multidrug-resistant tuberculosis[J]. Chin J Antituberc,2020,42(1):38-43., articleTitle=Analysis of CT findings in patients with initial and retreated multidrug-resistant tuberculosis, refAbstract=null), Reference(id=1322191093324694203, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1021/acs.molpharmaceut.7b00875, pmid=null, pmcid=null, year=2018, volume=15, issue=10, pageStart=4326, pageEnd=4335, url=null, language=null, rfNumber=25, rfOrder=32, authorNames=GAO X W, QIAN Y, journalName=Mol Pharm, refType=null, unstructuredReference=GAO X W,QIAN Y. Prediction of multidrug-resistant TB from CT pulmonary images based on deep learning techniques[J]. Mol Pharm,2018,15(10):4326-4335., articleTitle=Prediction of multidrug-resistant TB from CT pulmonary images based on deep learning techniques, refAbstract=null), Reference(id=1322191093387608764, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1007/s00330-022-08997-9, pmid=null, pmcid=null, year=2023, volume=33, issue=1, pageStart=391, pageEnd=400, url=null, language=null, rfNumber=26, rfOrder=33, authorNames=LI Y, WANG B, WEN L M, journalName=Eur Radiol, refType=null, unstructuredReference=LI Y,WANG B,WEN L M,et al. Machine learning and radiomics for the prediction of multidrug resistance in cavitary pulmonary tuberculosis:a multicentre study[J]. Eur Radiol,2023,33(1):391-400., articleTitle=Machine learning and radiomics for the prediction of multidrug resistance in cavitary pulmonary tuberculosis:a multicentre study, refAbstract=null), Reference(id=1322191093467300541, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1007/s11548-018-1857-9, pmid=null, pmcid=null, year=2018, volume=13, issue=12, pageStart=1915, pageEnd=1925, url=null, language=null, rfNumber=27, rfOrder=34, authorNames=JAEGER S, JUAREZ-ESPINOSA O H, CANDEMIR S, journalName=Int J Comput Assist Radiol Surg, refType=null, unstructuredReference=JAEGER S,JUAREZ-ESPINOSA O H,CANDEMIR S,et al. Detecting drug-resistant tuberculosis in chest radiographs[J]. Int J Comput Assist Radiol Surg,2018,13(12):1915-1925., articleTitle=Detecting drug-resistant tuberculosis in chest radiographs, refAbstract=null), Reference(id=1322191093534409406, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, doi=10.1002/mco2.487, pmid=null, pmcid=null, year=2024, volume=5, issue=3, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=35, authorNames=LIANG S F, XU X Y, YANG Z, journalName=MedComm, refType=null, unstructuredReference=LIANG S F,XU X Y,YANG Z,et al. Deep learning for precise diagnosis and subtype triage of drug-resistant tuberculosis on chest computed tomography[J]. MedComm (2020),2024,5(3):e487., articleTitle=Deep learning for precise diagnosis and subtype triage of drug-resistant tuberculosis on chest computed tomography, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])], figs=[ArticleFig(id=1322191086110491273, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, label=null, caption=null, figureFileSmall=6+9Bc0rfcHMnVARX0DvhPQ==, figureFileBig=jObQ6Puv9AbpNNo6bk0GEA==, tableContent=null), ArticleFig(id=1322191086215348874, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, label=图1, caption=总体研究流程, figureFileSmall=6+9Bc0rfcHMnVARX0DvhPQ==, figureFileBig=jObQ6Puv9AbpNNo6bk0GEA==, tableContent=null), ArticleFig(id=1322191086454424203, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, label=null, caption=null, figureFileSmall=eXcD8NmMbKOUkKNFgoPl3Q==, figureFileBig=tfa2ZaRvdCT74oCWfvzyiQ==, tableContent=null), ArticleFig(id=1322191086538310284, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, label=图2, caption=药物敏感肺结核(A)与耐药肺结核(B)胸部CT影像, figureFileSmall=eXcD8NmMbKOUkKNFgoPl3Q==, figureFileBig=tfa2ZaRvdCT74oCWfvzyiQ==, tableContent=null), ArticleFig(id=1322191088207643277, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, label=null, caption=null, figureFileSmall=0l3I5EyuQ+x9WMzd/lC3mQ==, figureFileBig=oLiNAX+LBp8mvzOFLTwbAA==, tableContent=null), ArticleFig(id=1322191088291529358, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, label=图3, caption=胸部CT影像肺实质区域的自动分割

A:胸部CT;B:分割掩膜;C:肺实质区域

, figureFileSmall=0l3I5EyuQ+x9WMzd/lC3mQ==, figureFileBig=oLiNAX+LBp8mvzOFLTwbAA==, tableContent=null), ArticleFig(id=1322191088375415439, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, label=null, caption=null, figureFileSmall=K7c9qOa8Ru3fKrTS16/0IQ==, figureFileBig=fn1t7XdSDjDoIV+7yqR5hg==, tableContent=null), ArticleFig(id=1322191088471884432, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, label=图4, caption=不同模型识别耐药肺结核的ROC曲线, figureFileSmall=K7c9qOa8Ru3fKrTS16/0IQ==, figureFileBig=fn1t7XdSDjDoIV+7yqR5hg==, tableContent=null), ArticleFig(id=1322191088538993297, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, label=null, caption=null, figureFileSmall=oLv/ERlK3QPRHx+zPkeOiQ==, figureFileBig=OYljQWrawOvI8Edpn/5Sew==, tableContent=null), ArticleFig(id=1322191088627073682, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, label=图5, caption=3D ResNet18模型与不同年资放射科医师识别耐药肺结核的性能对比, figureFileSmall=oLv/ERlK3QPRHx+zPkeOiQ==, figureFileBig=OYljQWrawOvI8Edpn/5Sew==, tableContent=null), ArticleFig(id=1322191088706765459, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, label=null, caption=null, figureFileSmall=Qp+UveqrFINTclLMEqcI1A==, figureFileBig=WL+ATQkqUI8gjQ4RtTfRyg==, tableContent=null), ArticleFig(id=1322191088799040148, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, label=图6, caption=自动分割的肺实质区域及生成的类激活映射图

A:耐药肺结核肺实质区域; B:耐药肺结核类激活映射; C:药物敏感肺结核肺实质区域; D:药物敏感肺结 核类激活映射

, figureFileSmall=Qp+UveqrFINTclLMEqcI1A==, figureFileBig=WL+ATQkqUI8gjQ4RtTfRyg==, tableContent=null), ArticleFig(id=1322191088882926229, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
类别训练集测试集总计
药物敏感肺结核29067357
耐药肺结核28877365
总计578144722
), ArticleFig(id=1322191088971006614, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, label=表1, caption=

训练集与测试集的影像数据划分情况(例)

, figureFileSmall=null, figureFileBig=null, tableContent=
类别训练集测试集总计
药物敏感肺结核29067357
耐药肺结核28877365
总计578144722
), ArticleFig(id=1322191089054892695, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
深度学习网络灵敏度特异度阳性预测值阴性预测值AUCF1值
3D Swin Transformer0.455(0.343,0.566)0.746(0.638,0.843)0.673(0.542,0.790)0.543(0.447,0.639)0.583(0.488,0.676)0.543
3D ViT0.857(0.781,0.930)0.507(0.383,0.623)0.667(0.573,0.755)0.756(0.628,0.872)0.698(0.606,0.786)0.750
3D ShuffleNet v20.636(0.524,0.737)0.701(0.591,0.841)0.710(0.600,0.827)0.627(0.506,0.750)0.704(0.616,0.788)0.671
3D DenseNet0.610(0.506,0.728)0.836(0.750,0.918)0.810(0.711,0.906)0.651(0.549,0.756)0.736(0.655,0.832)0.696
3D MobileNet v20.844(0.760,0.935)0.582(0.467,0.701)0.699(0.605,0.789)0.765(0.642,0.877)0.758(0.674,0.831)0.765
3D ResNet180.935(0.880,0.987)0.642(0.492,0.757)0.750(0.663,0.835)0.896(0.809,0.976)0.841(0.774,0.903)0.832
), ArticleFig(id=1322191089134584472, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, label=表2, caption=

不同模型对耐药肺结核的识别性能比较 [OR(95%CI)]

, figureFileSmall=null, figureFileBig=null, tableContent=
深度学习网络灵敏度特异度阳性预测值阴性预测值AUCF1值
3D Swin Transformer0.455(0.343,0.566)0.746(0.638,0.843)0.673(0.542,0.790)0.543(0.447,0.639)0.583(0.488,0.676)0.543
3D ViT0.857(0.781,0.930)0.507(0.383,0.623)0.667(0.573,0.755)0.756(0.628,0.872)0.698(0.606,0.786)0.750
3D ShuffleNet v20.636(0.524,0.737)0.701(0.591,0.841)0.710(0.600,0.827)0.627(0.506,0.750)0.704(0.616,0.788)0.671
3D DenseNet0.610(0.506,0.728)0.836(0.750,0.918)0.810(0.711,0.906)0.651(0.549,0.756)0.736(0.655,0.832)0.696
3D MobileNet v20.844(0.760,0.935)0.582(0.467,0.701)0.699(0.605,0.789)0.765(0.642,0.877)0.758(0.674,0.831)0.765
3D ResNet180.935(0.880,0.987)0.642(0.492,0.757)0.750(0.663,0.835)0.896(0.809,0.976)0.841(0.774,0.903)0.832
), ArticleFig(id=1322191089247830681, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
不同年资医师与模型灵敏度P特异度P阳性预测值P阴性预测值P值F1
低年资医师10.597
(0.487,0.704)
<0.0010.433
(0.302,0.543)
0.0190.548
(0.440,0.650)
<0.0010.483
(0.358,0.600)
<0.0010.571
低年资医师20.377
(0.269,0.488)
<0.0010.657
(0.541,0.770)
0.8540.558
(0.420,0.684)
0.0020.478
(0.389,0.583)
<0.0010.450
中等年资
医师1
0.701
(0.605,0.802)
0.0050.567
(0.447,0.684)
0.4240.651
(0.549,0.757)
0.0320.623
(0.500,0.754)
<0.0010.675
中等年资
医师2
0.61
(0.500,0.714)
<0.0010.597
(0.483,0.722)
0.6250.635
(0.524,0.740)
0.0260.571
(0.464,0.685)
<0.0010.623
高年资
医师1
0.649
(0.538,0.753)
<0.0010.478
(0.358,0.594)
0.0760.588
(0.479,0.701)
0.0020.542
(0.421,0.677)
<0.0010.617
高年资
医师2
0.701
(0.597,0.811)
0.0020.418
(0.303,0.536)
0.0110.581
(0.480,0.677)
<0.0010.549
(0.417,0.682)
<0.0010.635
3D ResNet180.935
(0.880,0.987)
0.642
(0.492,0.757)
0.750
(0.663,0.835)
0.896
(0.809,0.976)
0.832
), ArticleFig(id=1322191089335911066, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, language=CN, label=表3, caption=

3D ResNet18与不同年资放射科医师在耐药肺结核识别中的性能指标比较 [OR(95%CI)]

, figureFileSmall=null, figureFileBig=null, tableContent=
不同年资医师与模型灵敏度P特异度P阳性预测值P阴性预测值P值F1
低年资医师10.597
(0.487,0.704)
<0.0010.433
(0.302,0.543)
0.0190.548
(0.440,0.650)
<0.0010.483
(0.358,0.600)
<0.0010.571
低年资医师20.377
(0.269,0.488)
<0.0010.657
(0.541,0.770)
0.8540.558
(0.420,0.684)
0.0020.478
(0.389,0.583)
<0.0010.450
中等年资
医师1
0.701
(0.605,0.802)
0.0050.567
(0.447,0.684)
0.4240.651
(0.549,0.757)
0.0320.623
(0.500,0.754)
<0.0010.675
中等年资
医师2
0.61
(0.500,0.714)
<0.0010.597
(0.483,0.722)
0.6250.635
(0.524,0.740)
0.0260.571
(0.464,0.685)
<0.0010.623
高年资
医师1
0.649
(0.538,0.753)
<0.0010.478
(0.358,0.594)
0.0760.588
(0.479,0.701)
0.0020.542
(0.421,0.677)
<0.0010.617
高年资
医师2
0.701
(0.597,0.811)
0.0020.418
(0.303,0.536)
0.0110.581
(0.480,0.677)
<0.0010.549
(0.417,0.682)
<0.0010.635
3D ResNet180.935
(0.880,0.987)
0.642
(0.492,0.757)
0.750
(0.663,0.835)
0.896
(0.809,0.976)
0.832
)], attaches=null, journal=Journal(id=1319372634082869396, delFlag=0, nameCn=陆军军医大学学报, nameEn=Journal of Army Medical University, nameHistory1=null, nameHistory2=null, issn=2097-0927, eissn=null, cn=50-1223/R, coden=null, periodic=3, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=zdiTazv9TbsMJqLaCJ/k7A==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Army Medical University, journalRemark=null, publicationField=null, createdTime=1792492548725, updatedTime=1792745216517, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=L, firstLetterEn=L, subjectCode=Medical and Pharmaceutical Sciences, subjectName=null, subjectCodeEn=Medical and Pharmaceutical Sciences, subjectNameEn=null, picCn=zdiTazv9TbsMJqLaCJ/k7A==, picEn=931BgeD2k9AIsc7QjHoQKg==, jcr=null, cjcr=null, exts=[JournalExt(id=1320432400862135101, language=CN, name=陆军军医大学学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1792745216813, updatedTime=1792745216813, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://ljjydx.portal.founderss.cn, submissionEditorUrl=https://journal.ids.fzyun.cn, submissionReviewUrl=https://ljjydx.portal.founderss.cn, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1320432400933438270, language=EN, name=Journal of Army Medical University, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1792745216830, updatedTime=1792745216830, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://ljjydx.portal.founderss.cn, submissionEditorUrl=https://journal.ids.fzyun.cn, submissionReviewUrl=https://ljjydx.portal.founderss.cn, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1319373162502258839, websiteList=[Website(id=1319376331821925278, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1319373162502258839, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/ljjydxxb/CN, language=CN, createTime=1792493430333, createBy=18614031015, updateTime=1792493552921, updateBy=18614031015, name=陆军军医大学学报-中文, tplId=1146099689490845704, title=陆军军医大学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1319376971570729589, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331821925278, code=articleTextType, value=kx, createTime=1792493582861, updateTime=1792493582861, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376971549758066, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331821925278, code=banner, value=null, createTime=1792493582856, updateTime=1792493582856, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376971591701112, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331821925278, code=grayFlag, value=0, createTime=1792493582866, updateTime=1792493582866, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376971541369457, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331821925278, code=logo, value=https://castjournals.cast.org.cn/joweb/ljjydxxb/CN/file/pic?fileId=Mmvh7crXM7dcUwf9n9+ehg==, createTime=1792493582854, updateTime=1792493582854, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376971608478330, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331821925278, code=minRunFlag, value=0, createTime=1792493582870, updateTime=1792493582870, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376971562340980, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331821925278, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ljjydxxb/CN/file/pic, createTime=1792493582859, updateTime=1792493582859, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376971600089721, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331821925278, code=silenceFlag, value=0, createTime=1792493582868, updateTime=1792493582868, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376971558146675, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331821925278, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1792493582858, updateTime=1792493582858, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376971574923894, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331821925278, code=themeColor, value=null, createTime=1792493582862, updateTime=1792493582862, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376971583312503, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331821925278, code=themeStyle, value=null, createTime=1792493582864, updateTime=1792493582864, creator=18614031015, updator=18614031015)]), Website(id=1319376331905811365, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1319373162502258839, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/ljjydxxb/EN, language=EN, createTime=1792493430353, createBy=18614031015, updateTime=1792493548158, updateBy=18614031015, name=陆军军医大学学报-英文, tplId=1146101810881728533, title=Journal of Army Medical University, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1319376935873008230, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331905811365, code=articleTextType, value=kx, createTime=1792493574350, updateTime=1792493574350, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376935843648099, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331905811365, code=banner, value=null, createTime=1792493574343, updateTime=1792493574343, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376935902368361, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331905811365, code=grayFlag, value=0, createTime=1792493574357, updateTime=1792493574357, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376935835259490, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331905811365, code=logo, value=https://castjournals.cast.org.cn/joweb/ljjydxxb/EN/file/pic?fileId=Mmvh7crXM7dcUwf9n9+ehg==, createTime=1792493574341, updateTime=1792493574341, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376935914951275, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331905811365, code=minRunFlag, value=0, createTime=1792493574360, updateTime=1792493574360, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376935864619621, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331905811365, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ljjydxxb/EN/file/pic, createTime=1792493574348, updateTime=1792493574348, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376935906562666, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331905811365, code=silenceFlag, value=0, createTime=1792493574358, updateTime=1792493574358, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376935856231012, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331905811365, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1792493574346, updateTime=1792493574346, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376935881396839, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331905811365, code=themeColor, value=null, createTime=1792493574352, updateTime=1792493574352, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376935889785448, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331905811365, code=themeStyle, value=null, createTime=1792493574354, updateTime=1792493574354, creator=18614031015, updator=18614031015)])], journalTitle=陆军军医大学学报, weixinUrl=null, journalUrl=https://aammt.tmmu.edu.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Army Medical University, journalPhotoCn=zdiTazv9TbsMJqLaCJ/k7A==, journalPhotoEn=931BgeD2k9AIsc7QjHoQKg==, journalFirstLetter=L, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/ljjydxxb/CN/10.16016/j.2097-0927.202504117, detailUrlEn=https://castjournals.cast.org.cn/joweb/ljjydxxb/EN/10.16016/j.2097-0927.202504117, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ljjydxxb/CN/PDF/10.16016/j.2097-0927.202504117, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ljjydxxb/EN/PDF/10.16016/j.2097-0927.202504117, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1753804800000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于CT影像的3D ResNet18模型在肺结核耐药性识别中的预测性能研究
收藏切换
PDF下载
李春华 , 刘雪艳 , 郑娇凤 , 曾祥鑫 , 李玉蕊 , 刘雯雯 , 吕圣秀
陆军军医大学学报 | 生物医学工程 2025,47(14): 1676-1684
收起
收藏切换
陆军军医大学学报 |生物医学工程 2025 , 47 (14) : 1676 -1684
基于CT影像的3D ResNet18模型在肺结核耐药性识别中的预测性能研究
全屏
[Author(id=1322191082075570783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191083757486689, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191082075570783, language=EN, stringName=Chunhua LI, firstName=Chunhua, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191083837178466, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191082075570783, language=CN, stringName=李春华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191083916870244, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191084013339238, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191083916870244, language=EN, stringName=Xueyan LIU, firstName=Xueyan, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191084093031015, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191083916870244, language=CN, stringName=刘雪艳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191084181111401, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191084273386091, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084181111401, language=EN, stringName=Jiaofeng ZHENG, firstName=Jiaofeng, middleName=null, lastName=ZHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191084361466476, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084181111401, language=CN, stringName=郑娇凤, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191084445352558, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191084537627248, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084445352558, language=EN, stringName=Xiangxin ZENG, firstName=Xiangxin, middleName=null, lastName=ZENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191084613124721, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084445352558, language=CN, stringName=曾祥鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191084684427891, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191084755731061, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084684427891, language=EN, stringName=Yurui LI, firstName=Yurui, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191084806062710, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084684427891, language=CN, stringName=李玉蕊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191084868977272, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322191084952863354, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084868977272, language=EN, stringName=Wenwen LIU, firstName=Wenwen, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191085032555131, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191084868977272, language=CN, stringName=刘雯雯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])]), Author(id=1322191085099663997, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=r202206@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322191085179355775, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191085099663997, language=EN, stringName=Shengxiu LYU, firstName=Shengxiu, middleName=null, lastName=LYU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322191085242270336, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, authorId=1322191085099663997, language=CN, stringName=吕圣秀, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=1重庆市公共卫生医疗救治中心医学影像科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322191081991684699, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, xref=1, ext=[AuthorCompanyExt(id=1322191082000073308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China), AuthorCompanyExt(id=1322191082008461917, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322191080204911180, companyId=1322191081991684699, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市公共卫生医疗救治中心医学影像科,重庆)])])]
李春华, 刘雪艳, 郑娇凤, 曾祥鑫, 李玉蕊, 刘雯雯, 吕圣秀
作者信息
  • 1重庆市公共卫生医疗救治中心医学影像科,重庆
通讯作者:
吕圣秀,E-mail:
LYU Shengxiu,E-mail:
Predictive performance of CT images-based 3D ResNet18 model for identifying lung tuberculosis drug resistance
Chunhua LI, Xueyan LIU, Jiaofeng ZHENG, Xiangxin ZENG, Yurui LI, Wenwen LIU, Shengxiu LYU
Affiliations
  • 1Department of Medical Imaging,Chongqing Public Health Medical Center,Chongqing,China
出版时间: 2025-07-30 doi: 10.16016/j.2097-0927.202504117
文章导航
收藏切换
目的

通过构建并验证一种基于胸部CT影像的深度学习模型,以正确识别耐药肺结核和药物敏感肺结核。

方法

回顾性纳入重庆市公共卫生医疗救治中心2019年1月至2022年12月诊治的722例继发性肺结核CT影像,根据药物敏感性试验结果,将其分为药物敏感肺结核组和耐药肺结核组,其中药物敏感肺结核357例,耐药肺结核365例。采用U-Net分割模型预先对CT影像的肺实质区域进行分割,然后按8∶2的比例随机划分为训练集和测试集。评估6种三维深度学习网络(3D Swin Transformer、3D ShuffleNet v2、3D ViT、3D MobileNet v2、3D DenseNet及3D ResNet18)对肺结核耐药性的识别性能,在训练集上通过五折交叉验证调整超参数,以构建最优深度学习模型。采用曲线下面积(area under the curve,AUC)、灵敏度、特异度、阳性预测值(positive predictive value,PPV)、阴性预测值(negative predictive value,NPV)以及F1值评价模型性能。由6名放射科医师对测试集CT影像进行耐药性识别,并与性能最优的深度学习模型进行性能比较。

结果

3D Swin Transformer、3D ShuffleNet v2、3D ViT、3D MobileNet v2、3D DenseNet及3D ResNet18预测耐药肺结核的AUC分别为0.583、0.704、0.698、0.758、0.736及0.841,3D ResNet18为性能最优深度学习模型,其灵敏度为0.935(95%CI:0.880~0.987),特异度为0.642(95%CI:0.492~0.757),阳性预测值为0.750(95%CI:0.663~0.835),阴性预测值为0.896(95%CI:0.809~0.976),AUC值为0.841,F1值为0.832。放射科医师F1值分别为0.571、0.450、0.675、0.623、0.617、0.635,3D ResNet18模型F1值均高于放射科医师。识别耐药肺结核结果最优的放射科医师的灵敏度、特异度、阳性预测值、阴性预测值分别为0.701(95%CI:0.605~0.802)、0.567(95%CI:0.447~0.684)、0.651(95%CI:0.549~0.757)、0.623(95%CI:0.500~0.754),其灵敏度、阳性预测值和阴性预测值均低于3D ResNet18模型(P<0.05)。类激活映射图表明3D ResNet18能够关注到关键病变区域。

结论

3D ResNet18 模型在肺结核耐药性识别中预测性能最优,有望辅助临床诊断耐药肺结核。

深度学习  /  肺结核  /  耐药性  /  药物敏感
Objective‍

To develop and validate a deep learning model based on chest CT images to accurately distinguish between drug-resistant (DR-TB) and -sensitive tuberculosis (DS-TB).

Methods‍

A retrospective study was conducted on 722 cases of confirmed secondary tuberculosis admitted in our center from January 2019 to December 2022. According to the results of antimicrobial susceptibility test, they were divided into 357 DS-TB cases and 365 DR-TB cases. Pre-existing U-Net segmentation model was employed to segment the lung parenchyma regions in CT images. The dataset was randomly partitioned into a training set and a testing set in an 8:2 ratio. Six 3D deep learning architectures (3D Swin Transformer, 3D ShuffleNet v2, 3D ViT, 3D MobileNet v2, 3D DenseNet, and 3D ResNet18) were employed to evaluate the discriminative efficiency between DS-TB and DR-TB. Hyperparameters were optimized by five-fold cross-validation on the training set to construct the optimal model. The performance of the constructed model was assessed using area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score. Six radiologists independently evaluated DR-TB identification on the test set, and their performance was compared with the best-performing deep learning model.

Results‍

The AUC value in DR-TB prediction was 0.583, 0.704, 0.698, 0.758, 0.736, and 0.841, respectively, for 3D Swin Transformer, 3D ShuffleNet v2, 3D ViT, 3D MobileNet v2, 3D DenseNet, and 3D ResNet18. The 3D ResNet18 model demonstrated optimal performance, achieving a sensitivity of 0.935 (95%CI: 0.880~0.987), a specificity of 0.642 (95%CI: 0.492~0.757), a PPV of 0.750 (95%CI: 0.663~0.835), an NPV of 0.896 (95%CI: 0.809~0.976), an AUC value of 0.841, and a F1-score of 0.832. The radiologists got a F1-score of 0.571, 0.450, 0.675, 0.623, 0.617 and 0.635, respectively, and the F1-score of the 3D ResNet18 model is all higher than that of the radiologists. The highest-performing radiologist achieved sensitivity, specificity, PPV and NPV of 0.701 (95%CI: 0.605~0.802), 0.567 (95%CI: 0.447~0.684), 0.651 (95%CI: 0.549~0.757), and 0.623 (95%CI: 0.500~0.754), with all these values lower than those of the 3D ResNet18 model (P<0.05). Class activation mapping showed that the 3D ResNet18 model could focus on key lesion areas. The class activation mapping demonstrated that the 3D ResNet18 model could effectively focus on critical lesion regions.

Conclusion‍

Our 3D ResNet18 model shows the best predictive performance in identifying DR-TB, and is expected to assist clinical diagnosis for DR-TB.

deep learning  /  tuberculosis  /  drug resistance  /  drug susceptibility
李春华, 刘雪艳, 郑娇凤, 曾祥鑫, 李玉蕊, 刘雯雯, 吕圣秀. 基于CT影像的3D ResNet18模型在肺结核耐药性识别中的预测性能研究. 陆军军医大学学报, 2025 , 47 (14) : 1676 -1684 . DOI: 10.16016/j.2097-0927.202504117
Chunhua LI, Xueyan LIU, Jiaofeng ZHENG, Xiangxin ZENG, Yurui LI, Wenwen LIU, Shengxiu LYU. Predictive performance of CT images-based 3D ResNet18 model for identifying lung tuberculosis drug resistance[J]. Journal of Army Medical University, 2025 , 47 (14) : 1676 -1684 . DOI: 10.16016/j.2097-0927.202504117
耐药肺结核是指结核分枝杆菌对一种或多种抗结核药物产生了耐药性,其防治已成为全球公共卫生领域的重大挑战。2024年全球结核病报告指出,2023年全球新增40万例耐多药/利福平耐药结核病,复治患者耐药率高达16%,而在30个结核病高负担国家中,中国耐药结核患者数量约占全球7.3%,位列全球第4[1]。耐药肺结核的治疗比药物敏感肺结核需要更长的时间和更高的经济成本[2],且治愈率低,我国的治疗成功率仅为51%[3],显著低于全球平均水平[1]。这不仅严重威胁患者个体健康,更因疾病传播风险加剧,给社会医疗资源带来沉重负担。
耐药肺结核的早期诊断对其治疗方案的选择至关重要。结核分枝杆菌培养和药物敏感性试验是耐药肺结核诊断的金标准,但耗时较长,常需4~8周,难以满足临床早期诊断的需求。分子生物学及基因检测虽能快速诊断,但昂贵的费用与严苛的技术条件,使其在基层医院难以推广[4]。此外,部分患者为菌阴肺结核,无法通过实验室方法找到病原菌,导致耐药肺结核的诊断率不到50%[2],大量患者未能及时得到治疗。胸部CT检查在耐药肺结核诊断中有一定作用,但药物敏感肺结核和耐药肺结核影像交叉重叠大,仅依靠影像医师对CT影像的解读来判断肺结核是否耐药准确性尚待提高[5]。深度学习作为人工智能领域的核心技术,其快速发展已成功应用于多种疾病的影像诊断,尤其是在肺结节及肿瘤诊断方面,大幅提高了诊断的准确性和效率[6-8],然而,该技术在肺结核的耐药性识别方面仍处于起步阶段,现有研究多在初步模型构建层面,准确性和稳定性欠佳,整体识别效能与临床应用要求仍存在较大差距,难以满足临床对耐药肺结核精准诊断的需求,亟需进一步优化与提升。本研究通过构建肺结核患者胸部CT影像数据集,在精准提取肺实质分割的基础上,构建并验证一种基于胸部CT影像的深度学习模型,该模型通过挖掘CT影像中潜在特征,可以准确识别耐药肺结核和药物敏感肺结核,为临床医师提供一种快速、准确的辅助诊断工具,改变传统依赖医师主观判读CT影像的诊断模式,满足重大公共卫生需求,推动医疗诊断技术革新,为耐药肺结核的防控提供新的有效诊疗手段。
本研究聚焦耐药肺结核与药物敏感肺结核的识别问题,通过胸部CT影像的深度学习构建相应的模型加以解决,其总体研究流程如图1所示。通过构建包含耐药肺结核与药物敏感肺结核两种类别的继发性肺结核患者的胸部CT影像数据集,利用U-Net模型[9]自动分割出肺实质区域。在此基础上,引入6种典型的深度学习网络分别训练能够识别耐药肺结核与药物敏感肺结核的模型,通过比较不同模型的识别性能筛选出最优深度学习模型,并将最优模型进一步与6名放射科医师的识别性能进行比较,以评估最优模型在临床辅助诊断方面的应用潜力。
回顾性收集重庆市公共卫生医疗救治中心2019年1月至2022年12月收治的继发性肺结核患者的胸部CT影像,所有入组病例均通过BACTEC MGIT960系统液体培养及比例法进行药敏试验确诊是否耐药。纳入标准:①所有患者年龄≥18岁,有完整的胸部CT检查资料,且CT图像质量符合诊断要求[10];②肺结核诊断符合《WS288-2017肺结核诊断》[11],并进行药敏试验检测;③耐药肺结核包括对药物敏感试验中任何一种或多种抗结核药物耐药的肺结核,并未区分耐单药与耐多药。排除标准:①合并肺部肿瘤、尘肺及其他可能影响肺结核诊断的肺部病变患者;②HIV阳性、糖尿病或服用免疫抑制剂者。根据纳入排除标准最终收集722例肺结核患者胸部CT平扫影像,共30 496张CT影像,其中药物敏感肺结核357例(男性178例、女性179例),中位年龄43(28,56)岁;耐药肺结核365例(男性250例、女性115例),中位年龄46(28,56)岁。CT影像层厚均为5 mm,矩阵为512×512。药物敏感肺结核以及耐药肺结核的胸部CT影像如图2所示。
采用已公开的面向肺实质分割的U-Net模型对所有胸部CT影像进行肺部区域分割,该深度学习模型通过编码-解码的U型网络结构生成精确的二值化掩码图像,完整标注肺实质解剖轮廓。将掩码图像与原始CT相乘即可提取出肺实质区域(图3)。预先进行肺实质的分割可以使得模型更好地聚焦关键区域、排除周围组织的干扰,从而显著提升模型识别的效率与准确性。
在以上肺实质区域分割基础上,根据8∶2的比例将所有胸部CT影像随机划分为训练集与测试集,其中训练集578例,共24 409张CT影像;测试集144例,共6 087张CT影像(表1)。为了增加模型的泛化性能,本研究对训练集进行离线数据增强,通过对同一胸部CT样本进行多次抽样,将训练集规模扩充至1 500例用于模型训练,测试集则不进行数据增强。
由于胸部CT是三维影像,结核病灶在CT层内和相邻层间具有连续性分布及形态相关性。单纯的二维深度学习网络忽略了CT层间相关性,其识别性能受到限制。为了同时提取结核病变在CT层内与层间的语义特征,本研究引入三维深度学习网络训练模型。选择6种代表性的三维深度学习网络,分别是3D Swin Transformer、3D ShuffleNet v2、3D ViT、3D MobileNetv2、3D DenseNet以及3D ResNet 18。
3D Swin Transformer将经典Swin Transformer的层次化窗口自注意力机制扩展至三维空间,通过可学习的局部窗口划分和跨窗口移位策略,在降低计算复杂度的同时仍然能够捕捉CT影像中器官、病灶的立体空间依赖关系。3D ShuffleNet v2通过三维通道重排和轻量化模块设计,将二维高效分组卷积与逐点卷积扩展至三维空间,在降低计算复杂度的同时保留多尺度时空特征交互能力。3D ViT将CT影像划分为连续立方体块序列,通过全局自注意力机制建模体素间长程空间依赖关系,并引入可学习的三维位置编码保留空间结构信息。3D MobileNetv2基于倒置残差结构与线性瓶颈层,将二维轻量化设计扩展至三维空间,通过三维深度可分离卷积分层提取CT影像时空特征。3D DenseNet通过密集连接机制使得每个三维卷积层均与后续所有层直接相连,强制跨层级特征复用,在保留原始CT体素间空间拓扑关系的同时,显著提升梯度流动效率。3D ResNet通过引入三维卷积核替代传统二维卷积,结合残差跳跃连接设计,在深度网络中建模CT影像的时空特征,并缓解梯度消失问题。
本研究在扩充后的训练集上通过五折交叉验证来指导模型超参数的调整。网络训练优化方法确定为随机梯度下降法,损失函数选用交叉熵损失函数。训练周期设为50个epoch,后10个epoch停用Mosaic增强以消除潜在的数据偏倚。初始学习率设置为0.1,学习率调整采用OneCycle策略,即每10个epoch进行动态更新。数据增强方案包括随机旋转(±15°)、多尺度缩放(0.8~1.2倍)、随机裁剪以及Mosaic增强和对训练集进行离线数据增强。
深度学习模型的性能评价指标包括曲线下面积(area under the curve,AUC)、灵敏度、特异度、阳性预测值(positive predictive value,PPV)、阴性预测值(negative predictive value,NPV)以及F1值。采用Bootstrap重采样法(1 000次重复抽样)计算95%置信区间(95%CI),以评估指标估计值的统计稳定性与推断可靠性。此外,本研究通过设计人机对比实验进一步评估模型的诊断效能。由不同年资放射科医师(低年资:<5年;中等年资:5~15年;高年资:>15年)各2名对测试集进行独立诊断,对耐药肺结核的诊断参考《耐药肺结核影像学诊断专家共识》[12]中的影像表现特点,如空洞最大直径≥30 mm,空洞数量≥3个,空洞存在的区域≥3个肺叶,慢性病程表现如胸膜增厚、纵隔移位、支气管牵拉扩张等作为耐药肺结核的诊断依据。最终将最优模型的识别性能与放射科医师的识别性能进行对比分析。
使用PyCharm集成开发环境中Python语言进行模型构建与性能统计分析。采用AUC、灵敏度、特异度、PPV、NPV以及F1分数评估模型性能,采用Bootstrap重采样法(1 000次重复抽样)计算95%置信区间(95%CI),以评估指标估计值的统计稳定性与推断可靠性。以P<0.05为差异有统计学意义。
通过自动分割出肺实质区域的CT影像数据集训练得到的6种深度学习模型,对耐药肺结核的识别性能如表2所示。3D ResNet18展现出明显优势,其灵敏度、阴性预测值、AUC及F1值均远远高于其他模型。在特异度方面,3D ResNet18高于3D ViT和3D ShuffleNet v2,略低于其他3种模型。此外,3D ResNet18的阳性预测值低于3D DenseNet,高于其余4种模型。由于AUC和F1值是评价识别性能的综合指标,因此可以提示6种模型中3D ResNet18对耐药肺结核的综合识别性能最优。
对6种深度学习模型在耐药肺结核识别任务中的ROC曲线及对应AUC值进行定量分析后发现(图4),3D ResNet18模型的AUC值达到0.841,3D MobileNet v2与3D DenseNet分别获得0.758和0.736的AUC值,呈现性能下降趋势;3D SwinTransformer识别性能最低。提示3D ResNet18模型显著优于其他5种模型。
由3组不同年资的放射科医师(每组各2名)对测试集进行独立诊断后,将其诊断结果与3D ResNet18 模型对耐药肺结核识别性能结果进行对比分析,从表3可以看出,3D ResNet18模型灵敏度、阳性预测值、阴性预测值几乎均高于医师(P<0.05);特异度高于一名高年资和低年资医师(P<0.05),与其余医师特异度相当;低年资放射科医师F1值最低,中等年资与高年资放射科医师的F1值较为接近。3D ResNet18模型F1值均高于放射科医师。提示3D ResNet18模型对耐药肺结核的识别性能整体优于3组放射科医师,有助于提高放射科医师诊断耐药肺结核的准确率。
将每位放射科医师对耐药肺结核识别性能的识别结果以点的形式呈现,不同类型的点对应不同年资的医师。ROC曲线表征了3D ResNet18的性能,将3D ResNet18模型与不同组别医师对耐药肺结核的识别性能进行比较。在该曲线上选取约登指数点作为模型识别性能的量化指标。通过对比ROC曲线上的约登指数点与其他6名医师对应点的相对位置关系,可直观评估深度学习模型与放射科医师的性能差异。从图5可见,代表模型性能的约登指数点较6名医师的对应点更靠近图的左上角,提示3D ResNet18的识别性能优于不同年资的放射科医师。
对于3D ResNet18模型,自动分割的肺实质区域生成的类激活映射图,如图6所示。结果表明,深度学习模型的注意力区域主要聚焦胸部CT影像中的肺结核病变部位。通过针对这些具有病理学意义的区域进行决策分析,可有效保证识别结果的可靠性和鲁棒性。
随着人工智能技术在医学诊断中的广泛应用,多项研究已证实深度学习在结核病影像诊断中的应用潜力,其诊断能力已达到与放射科医师相当的水平[13-16]。HWANG等[14]基于深度学习的肺结核检测系统在胸部X线分类性能达0.977~1.000,优于放射科医师的判断。RAJPURKAR等[15]结合HIV患者临床与胸部X射线图像,使用深度学习算法将肺结核诊断AUC从0.60提升至0.79,特别适用于在HIV/TB感染负担较重地区。WANG等[16]建立的CT/X线双模态系统包括肺结核在内的主要呼吸疾病,其诊断中AUC达0.856~0.900,接近资深放射科医师水平。一项纳入23 954名患者的胸部X片的研究显示[17],AI算法在X线分析中AUC达90.81%,在保持90%灵敏度的同时,可减少50% Xpert检测需求。AI算法可成为结核病高负担地区准确有效的检测和分流工具。人工智能算法通过X线平片对肺结核进行分类,内部验证的AUC值达到了0.94,而通过影像特征建模的平均AUC值为0.84。外部验证结果显示,其诊断效能优于医师[18]。
然而,这些模型大多基于胸部X线平片开发,CT容积图像能展示更复杂组织结构的差异和细微特征。近年来基于CT影像的人工智能的二分类研究多为肺炎及肿瘤的鉴别诊断[19-20],如BAI等[21]开发的胸部CT AI辅助系统显著提升放射科医师鉴别COVID-19与其他肺炎的准确性。但通过3D模型进行诊断肺结核,尤其是对耐药肺结核的诊断并不多见。SHI等[20]用胸部CT进行肺炎分类的深度学习模型中,在病毒性肺炎F1值达0.933,肺结核F1值仅为0.795。另一研究显示AI鉴别肺结核与非结核分枝杆菌肺病的AUC达0.826[22],而前期研究利用深度学习对继发性肺结核CT辅助诊断时,AUC达90.6%[23],与放射科中等年资医师的诊断水准相当。虽然深度学习对肺结核的诊断准确性较高,但耐药肺结核药与药物敏感肺结核病理和影像表现相似,尤其是初治耐药肺结核的早期,CT改变多表现为小叶中心性结节及树芽征和小片状实变,与药物敏感肺结核并没有太大差异[24]。GAO等[25]通过深度学习利用3D肺部CT图像预测耐多药结核病,但其数据集较少,准确性仅为64.71%。LI等[26]提取耐药肺结核空洞影像组学特征构建模型预测耐多药结核,AUC达到0.844,但仅从分割出的空洞提取特征,并未考虑肺部其他征象与空洞之间的相互联系。
3D ResNet18通过三维卷积操作能够有效捕捉肺结核病灶空间和层间的连续性特征;此外,残差结构支持更深层次的特征学习,有助于提取出语义性更强的深度特征,尤其适用于CT等立体数据的分类识别任务。本研究对训练集进行离线数据增强,通过对同一样本多次抽样的方式,将训练集数据进行扩充,有助于增强模型的泛化性能。实验结果表明,3D ResNet18模型在测试集上AUC值为0.841,F1值为0.832,显著优于其他5种三维卷积神经网络架构,尤其是3D ResNet18在灵敏度上的优势对减少漏诊尤为重要。JAEGER等[27]使用人工神经网络结合形状和纹理特征来区分药物敏感性和耐药性结核病时,其AUC仅为0.66。本研究通过三维网络架构进一步提升AUC,且灵敏度(0.935)亦有明显提高。虽然有学者通过手动标注进行肺结核耐药性研究,对耐药结核诊断F1值达到0.840[28],略高于本模型的F1值,但通过手动标注可能遗漏微小或非典型病灶,无法完整勾勒病变三维形态,标注误差可能传播形成系统性偏差,限制模型泛化性能。本研究采用无监督深度学习方法,无需大量人工标注数据,可自动从海量CT影像中提取关键特征,挖掘数据潜在关联,既降低数据预处理时间,又能减少人为判读误差,让模型训练更高效、诊断结果更可靠,提升耐药肺结核诊断的准确性与时效性。
本模型与不同年资医师相比,其灵敏度(0.935)与F1值(0.832)明显高于不同年资放射科医师,特别是与低年资医师组相比(F1值0.832 vs 0.571),表明其在检测耐药肺结核时极少漏诊,且综合性能更优。此外,其PPV(0.750)和NPV(0.896)也较高,说明模型预测阳性和阴性结果的准确性更突出。尽管模型的特异度未达最高,但综合灵敏度与特异度的平衡(F1值),模型表现最佳,凸显了深度学习在处理复杂影像特征上的优势。中高年资对耐药性的识别准确性比较一致,但均低于模型的综合识别能力。虽然多发空洞、厚壁空洞及慢性病变可以作为耐药肺结核的CT影像特征,但其与药物敏感肺结核存在交叉重叠,部分病变缺乏耐药肺结核的典型影像表现,通过肉眼很难准确判断是否耐药。且CT检查存在人眼识别盲区,肺尖等特殊部位的早期细微病变易被遗漏。而本研究构建的数据集包含的耐药结核类型较为全面,包括单耐药、利福平耐药、耐多药及广泛耐药等在内的绝大多数类型,复杂的影像学表现增加了放射科医师的识别难度。深度学习能够从大量胸部CT数据中自动提取出人眼难以察觉的关键病变特征,从而获得更好的识别性能,且识别结果具有较强的客观性和稳定性,这也是模型对耐药性识别整体性能优于放射科医师的原因之一。
尽管本研究取得了较为满意的结果,但仍存在以下局限:本研究数据为单中心回顾性数据,在一定程度上限制了模型泛化能力。未来可纳入多中心胸部CT影像数据增强模型的鲁棒性和泛化能力。此外,本研究数据仅包含影像数据,后续可考虑纳入临床及实验室检查信息,以进一步提高模型准确性。
综上所述,本研究基于肺结核患者胸部CT影像构建深度学习模型实现耐药肺结核的智能识别。研究结果表明,3D ResNet18 模型在肺结核耐药性识别任务中,性能显著优于其他对比模型,且综合诊断效能较不同年资放射科医师均呈现显著优势。本模型较传统方法可快速完成耐药性预测并缩短诊断时间,降低患者就医成本,节省医疗资源,可作为耐药肺结核的高效辅助诊断工具,对指导临床治疗、辅助个性化诊疗决策具有重要价值。后续研究计划纳入多中心影像学及临床数据,构建多模态深度学习模型,进一步提升模型识别性能,助力构建精准结核病防控体系。

参考文献 引证文献
排序方式:
1
World Health Organization. Global tuberculosis report 2024[EB/OL]. [2024-10-30].https://publichealthupdate.com/global-tuberculosis-report-2024/.
2
KARKI M,KANTIPUDI K,YANG F,et al. Generalization challenges in drug-resistant tuberculosis detection from chest X-rays[J]. Diagnostics (Basel),2022,12(1):188.
3
ZOU L P,KANG W L,GUO C H,et al. Treatment outcomes and associated influencing factors among patients with rifampicin-resistant tuberculosis:a multicenter,retrospective,cohort study in China[J]. Infect Drug Resist,2024,17:3737-3749.
4
CHEN M L,DODDI A,ROYER J,et al. Beyond multidrug resistance:Leveraging rare variants with machine and statistical learning models in Mycobacterium tuberculosis resistance prediction[J]. EBioMedicine,2019,43:356-369.
5
马璐瑶,郑秋婷,陆普选,等. 基于文献分析的耐多药肺结核影像学研究进展[J]. 新发传染病电子杂志,2021,6(1):65-72.
MA L Y,ZHENG Q T,LU P X,et al. Pulmonary multi-drug resistant tuberculosis:a radiological review[J]. Electron J Emerg Infect Dis,2021,6(1):65-72.
6
FENG B,CHEN X M,CHEN Y H,et al. Solitary solid pulmonary nodules:a CT-based deep learning nomogram helps differentiate tuberculosis granulomas from lung adenocarcinomas[J]. Eur Radiol,2020,30(12):6497-6507.
7
崔效楠,叶兆祥. 基于术前CT影像的肺结节病理类型预测模型研究[J]. 中华放射学杂志,2024,58(2):243-244.
CUI X N,YE Z X. Study on prediction model of pathological types of pulmonary nodules based on preoperative CT images[J]. Chin J Radiol,2024,58(2):243-244.
8
AFTAB J,KHAN M A,ARSHAD S,et al. Artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self-attention deep neural network architecture[J]. Sci Rep,2025,15:8724.
9
HOFMANNINGER J,PRAYER F,PAN J,et al. Automatic lung segmentation in routine imaging is primarily a data diversity problem,not a methodology problem[J]. Eur Radiol Exp,2020,4(1):50.
10
徐辉,岳保荣,尉可道,等.《X射线计算机体层摄影装置质量控制检测规范》解读[J]. 中国辐射卫生,2021,30(6):752-747,756.
XU H,YUE B R,WEI K D,et al. Interpretation of Specification for testing of quality control in X-ray computed tomography[J].Chin J Radiol Health,2021,30(6):752-747,756.
11
中华人民共和国国家卫生和计划生育委员会. WS 288—2017肺结核诊断[J]. 结核与肺部疾病杂志,2024,5(4):376-378.
National Health and Family Planning Commission of the People’s Republic of China.WS 288:2017 diagnosis of tuberculosis[J]. J Tuberc Lung Dis,2024,5(4):376-378.
12
中国研究型医院学会感染与炎症放射学专业委员会,中华医学会放射学分会传染病学组,中国科技产业化促进会数字健康专业委员会,等. 耐药肺结核影像学诊断专家共识[J]. 新发传染病电子杂志,2023,8(5):63-74.
Professional Committee of Infectious and Inflammatory Radiology of Chinese Research Hospital Association; Radiology Branch of Chinese Medical Association,Group of Infectious Diseases; China Association for the Promotion of Science and Technology Industrialization,Digital Health Professional Committee,et al. Expert consensus on imaging diagnosis of drug-resistant pulmonary tuberculosis[J].Electron J Emerg Infect Dis,2023,8(5):63-74.
13
KAZEMZADEH S,YU J,JAMSHY S,et al. Deep learning detection of active pulmonary tuberculosis at chest radiography matched the clinical performance of radiologists[J]. Radiology,2023,306(1):124-137.
14
HWANG E J,PARK S,JIN K N,et al. Development and validation of a deep learning-based automatic detection algorithm for active pulmonary tuberculosis on chest radiographs[J]. Clin Infect Dis,2019,69(5):739-747.
15
RAJPURKAR P,O’CONNELL C,SCHECHTER A,et al. CheXaid:deep learning assistance for physician diagnosis of tuberculosis using chest x-rays in patients with HIV[J]. NPJ Digit Med,2020,3:115.
16
WANG C D,MA J C,ZHANG S,et al. Development and validation of an abnormality-derived deep-learning diagnostic system for major respiratory diseases[J]. NPJ Digit Med,2022,5(1):124.
17
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.
18
DE CAMARGO T F O,RIBEIRO G A S,SILVA M C B DA,et al. Clinical validation of an artificial intelligence algorithm for classifying tuberculosis and pulmonary findings in chest radiographs[J]. Front Artif Intell,2025,8:1512910.
19
DENG J J,ZHAO M M,LI Q Y,et al. Implementation of artificial intelligence in the histological assessment of pulmonary subsolid nodules[J]. Transl Lung Cancer Res,2021,10(12):4574-4586.
20
SHI C Z,SHAO Y,SHAN F,et al. Development and validation of a deep learning model for multicategory pneumonia classification on chest computed tomography:a multicenter and multireader study[J]. Quant Imaging Med Surg,2023,13(12):8641-8656.
21
BAI H X,WANG R,XIONG Z,et al. Artificial intelligence augmentation of radiologist performance in distinguishing COVID-19 from pneumonia of other origin at chest CT[J]. Radiology,2021,299(1):E225.
22
李文婷,王丽,方勇,等. 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.
LI W T,WANG L,FANG Y,et al. The value of CT-based deep learning models in differentiating nontuberculous mycobacterial lung disease from pulmonary tuberculosis[J]. Chin J Antituberc,2024,46(10):1236-1242.
23
刘雪艳,王芳,李春华,等. 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.
LIU X Y,WANG F,LI C H,et al. Construction and evaluation of a CT-based deep learning model for the auxiliary diagnosis of secondary tuberculosis[J]. Chin J Antituberc,2024,46(3):279-287.
24
杨佳,吕圣秀,唐光孝,等. 初治与复治耐多药肺结核患者的CT表现分析[J]. 中国防痨杂志,2020,42(1):38-43.
YANG J,LYU S X,TANG G X,et al. Analysis of CT findings in patients with initial and retreated multidrug-resistant tuberculosis[J]. Chin J Antituberc,2020,42(1):38-43.
25
GAO X W,QIAN Y. Prediction of multidrug-resistant TB from CT pulmonary images based on deep learning techniques[J]. Mol Pharm,2018,15(10):4326-4335.
26
LI Y,WANG B,WEN L M,et al. Machine learning and radiomics for the prediction of multidrug resistance in cavitary pulmonary tuberculosis:a multicentre study[J]. Eur Radiol,2023,33(1):391-400.
27
JAEGER S,JUAREZ-ESPINOSA O H,CANDEMIR S,et al. Detecting drug-resistant tuberculosis in chest radiographs[J]. Int J Comput Assist Radiol Surg,2018,13(12):1915-1925.
28
LIANG S F,XU X Y,YANG Z,et al. Deep learning for precise diagnosis and subtype triage of drug-resistant tuberculosis on chest computed tomography[J]. MedComm (2020),2024,5(3):e487.
2025年第47卷第14期
PDF下载
20
6
引用本文
BibTeX
文章信息
doi: 10.16016/j.2097-0927.202504117
  • 接收时间:2025-04-29
  • 首发时间:2026-10-28
  • 出版时间:2025-07-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-04-29
  • 修回日期:2025-06-06
基金
作者信息
    1重庆市公共卫生医疗救治中心医学影像科,重庆

通讯作者:

吕圣秀,E-mail:
LYU Shengxiu,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ljjydxxb/CN/10.16016/j.2097-0927.202504117
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏