Article(id=1322934488413646862, tenantId=1146029695717560320, journalId=1319373162502258839, issueId=1322934434474885947, articleNumber=null, orderNo=null, doi=10.16016/j.2097-0927.202407001, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1719763200000, receivedDateStr=2024-07-01, revisedDate=1730217600000, revisedDateStr=2024-10-30, acceptedDate=null, acceptedDateStr=null, onlineDate=1793341760971, onlineDateStr=2026-10-30, pubDate=1736870400000, pubDateStr=2025-01-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793341760971, onlineIssueDateStr=2026-10-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793341760971, creator=13701087609, updateTime=1793341760971, updator=13701087609, issue=Issue{id=1322934434474885947, tenantId=1146029695717560320, journalId=1319373162502258839, year='2025', volume='47', issue='1', pageStart='1', pageEnd='99', issueExtLink='null', onlineDate='null', pubDate='1736870400000', pubDateStr='2025-01-15', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793341748111, creator='13701087609', updateTime=1793341748111, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=92, endPage=99, ext={EN=ArticleExt(id=1322934489927790611, articleId=1322934488413646862, tenantId=1146029695717560320, journalId=1319373162502258839, language=EN, title=Design of a mammography X-ray image classification assistant system adapted to Chinese population, columnId=1322190400052380037, journalTitle=Journal of Army Medical University, columnName=Biomedical Engineering, runingTitle=null, highlight=null, articleAbstract=
Objective‍

To construct a mammography image classification assistant system suitable for Chinese population,and explore the potential of artificial intelligence technology to assist early screening of breast cancer in China.

Methods‍

Curated breast imaging subset of digital database for screening mammography (CBIS-DDSM),Mammographic image analysis society database (MIAS) and other international open datasets were used to conduct model training respectively in order to reproduce the mainstream in-depth learning methods in the current literature. The model was also tested on the Chinese breast mammography database (CBMD) provided by Huajiao Technology Co.,Ltd,and the performance was compared. Aiming at the problem that the Chinese population data are not ideal in the performance test of the open dataset training model,an optimization strategy based on the sliding window adjustment mechanism was implemented in combination with the characteristics of Chinese population data. Then a two-stage migration learning method was designed to improve the overall performance of the model,and then development of our system was carried out.

Results‍

With the sliding window adjustment mechanism and the CBMD training model after two-stage transfer learning,the accuracy of our developed system was improved from 0.50 of the open datasets to 0.80,precision from 0.54 to 0.82,sensitivity from 0.52 to 0.80,F1 value from 0.52 to 0.80,and AUC value from 0.51 to 0.89 based on the Chinese population dataset as the test set.

Conclusion‍

Through the introduction of sliding window adjustment mechanism and two-stage migration learning strategy,the performance of the breast molybdenum target image classification model has been significantly improved in the Chinese population dataset,and our system primarily achieves the purpose of assisting the classification of breast molybdenum target images for the Chinese population.

, authors=Changjin SUN1, Fei TONG2, Yi WU3, Yuting WANG1, Junjie LUO1, Yan GONG1, Mingguo QIU1, Liang QIAO1, authorsList=Changjin SUN, Fei TONG, Yi WU, Yuting WANG, Junjie LUO, Yan GONG, Mingguo QIU, Liang QIAO, authorCompany=null, correspAuthors=Liang QIAO, 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=1322934490867314716, articleId=1322934488413646862, tenantId=1146029695717560320, journalId=1319373162502258839, language=CN, title=适应中国人群的乳腺钼靶X线图像分类辅助系统设计, 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

构建适应中国人群的乳腺钼靶图像分类辅助系统,探讨人工智能技术在国内辅助乳腺癌早期筛查的潜力。

方法

为复现当前文献中的主流深度学习方法,利用乳腺X线筛查数字数据库子集(curated breast imaging subset of digital database for screening mammography,CBIS-DDSM)、乳房X线图像分析学会数据库(mammographic image analysis society database,MIAS)等国际公开数据集分别进行模型训练,并在华教科技有限公司提供的中国人群乳腺钼靶图像数据集(Chinese breast mammography dataset,CBMD)上进行测试和模型性能比较;针对中国人群数据在公开数据集训练模型性能测试不理想的问题,结合中国人群数据特点,提出基于滑动窗口调窗机制的优化策略,设计二阶段迁移学习方法,以提升模型的整体性能,并进行系统研发。

结果

使用滑动窗口调窗机制及二阶段迁移学习后的CBMD训练模型,以中国人群数据集为测试集,其准确度从默认窗口下公开数据集训练模型的0.50提升至0.80,精度从0.54提升至0.82,灵敏度从0.52提升至0.80,F1值从0.52提升至0.80,AUC值从0.51提升至0.89。

结论

本研究引入滑动窗口调窗机制和二阶段迁移学习策略,显著提升了乳腺钼靶图像分类模型在中国人群数据集上的性能,初步达到适应中国人群的乳腺钼靶图像辅助分类的目的。

, authors=孙常晋1, 童飞2, 吴毅3, 王雨婷1, 罗俊捷1, 龚滟1, 邱明国1, 乔梁1, authorsList=孙常晋, 童飞, 吴毅, 王雨婷, 罗俊捷, 龚滟, 邱明国, 乔梁, authorCompany=null, correspAuthors=乔梁, authorNote=null, correspAuthorsNote=
乔梁,E-mail:
QIAO Liang,E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=MgRBjh1WJIkPRZ94AwHe0w==, magXml=e9mL7qGGKb3E5wnGZUuqDA==, pdfUrl=null, pdf=t69H3Eoh535Gei633h228g==, pdfFileSize=4706196, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=EYLCbGoA1uTMh5ZPtzpWqA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=F6fhcDdMbAqo1NgaK1xfNg==, mapNumber=null, fund=null)}, authors=[Author(id=1322934491387408423, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934491500654633, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491387408423, language=EN, stringName=Changjin SUN, firstName=Changjin, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934491571957802, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491387408423, language=CN, stringName=孙常晋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])]), Author(id=1322934491639066668, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934491718758446, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491639066668, language=EN, stringName=Fei TONG, firstName=Fei, middleName=null, lastName=TONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Department of Digital Medicine,Faculty of Biomedical Engineering and Imaging Medicine,Army Medical University (Third Military Medical University),Chongqing, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934491802644527, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491639066668, language=CN, stringName=童飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2陆军军医大学(第三军医大学)生物医学工程与影像医学系:数字医学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491198664736, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=2, ext=[AuthorCompanyExt(id=1322934491211247649, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491198664736, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Department of Digital Medicine,Faculty of Biomedical Engineering and Imaging Medicine,Army Medical University (Third Military Medical University),Chongqing, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491219636258, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491198664736, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2陆军军医大学(第三军医大学)生物医学工程与影像医学系:数字医学教研室,重庆)])]), Author(id=1322934491865559089, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934491936862259, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491865559089, language=EN, stringName=Yi WU, firstName=Yi, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Department of Medical Engineering, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934491991388212, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491865559089, language=CN, stringName=吴毅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3陆军特色医学中心(第三军医大学大坪医院)医学工程科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491282550819, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=3, ext=[AuthorCompanyExt(id=1322934491299328036, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491282550819, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Department of Medical Engineering, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491311910949, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491282550819, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3陆军特色医学中心(第三军医大学大坪医院)医学工程科,重庆)])]), Author(id=1322934492050108470, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934492117217336, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492050108470, language=EN, stringName=Yuting WANG, firstName=Yuting, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934492192714809, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492050108470, language=CN, stringName=王雨婷, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])]), Author(id=1322934492259823675, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934492335321149, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492259823675, language=EN, stringName=Junjie LUO, firstName=Junjie, middleName=null, lastName=LUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934492419207230, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492259823675, language=CN, stringName=罗俊捷, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])]), Author(id=1322934492494704704, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934492570202178, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492494704704, language=EN, stringName=Yan GONG, firstName=Yan, middleName=null, lastName=GONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934492633116739, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492494704704, language=CN, stringName=龚滟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])]), Author(id=1322934494302449733, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, orderNo=6, 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=1322934494398918727, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934494302449733, language=EN, stringName=Mingguo QIU, firstName=Mingguo, middleName=null, lastName=QIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934494478610505, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934494302449733, language=CN, stringName=邱明国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])]), Author(id=1322934494566690891, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, orderNo=7, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=bobq310@tmmu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322934494658965581, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934494566690891, language=EN, stringName=Liang QIAO, firstName=Liang, middleName=null, lastName=QIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934494734463054, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934494566690891, language=CN, stringName=乔梁, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])])], keywords=[Keyword(id=1322934494847709264, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=EN, orderNo=1, keyword=mammography), Keyword(id=1322934495086784593, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=EN, orderNo=2, keyword=deep learning), Keyword(id=1322934495153893458, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=EN, orderNo=3, keyword=X-Ray), Keyword(id=1322934495237779539, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=EN, orderNo=4, keyword=computer assistance), Keyword(id=1322934495317471316, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=CN, orderNo=1, keyword=乳腺钼靶), Keyword(id=1322934495392968789, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=CN, orderNo=2, keyword=深度学习), Keyword(id=1322934495460077654, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=CN, orderNo=3, keyword=X射线), Keyword(id=1322934495539769431, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=CN, orderNo=4, keyword=计算机辅助)], refs=[Reference(id=1322934496730951781, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.16506/j.1009-6639.2022.12.005, pmid=null, pmcid=null, year=2022, volume=23, issue=12, pageStart=909, pageEnd=916, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=高艳多, 阎炯, 赵胜, journalName=中国预防医学杂志, refType=null, unstructuredReference=高艳多,阎炯,赵胜,等. 1990—2019年中国女性乳腺癌发病和死亡趋势的年龄-时期-队列模型分析[J]. 中国预防医学杂志,2022,23(12):909-916., articleTitle=1990—2019年中国女性乳腺癌发病和死亡趋势的年龄-时期-队列模型分析, refAbstract=null), Reference(id=1322934496827420774, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.16506/j.1009-6639.2022.12.005, pmid=null, pmcid=null, year=2022, volume=23, issue=12, pageStart=909, pageEnd=916, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=GAO Y D, YAN J, ZHAO S, journalName=Chin Prev Med, refType=null, unstructuredReference=GAO Y D,YAN J,ZHAO S,et al. Trends in incidence and mortality of female breast cancer in China from 1990 to 2019 using age-period-cohort analysis model[J]. Chin Prev Med,2022,23(12):909-916., articleTitle=Trends in incidence and mortality of female breast cancer in China from 1990 to 2019 using age-period-cohort analysis model, refAbstract=null), Reference(id=1322934496902918247, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1038/s41597-023-02253-5, pmid=null, pmcid=null, year=2023, volume=10, issue=1, pageStart=334, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=XU Y Y, GONG M Y, WANG Y, journalName=Sci Data, refType=null, unstructuredReference=XU Y Y,GONG M Y,WANG Y,et al. Global trends and forecasts of breast cancer incidence and deaths[J]. Sci Data,2023,10(1):334., articleTitle=Global trends and forecasts of breast cancer incidence and deaths, refAbstract=null), Reference(id=1322934497011970152, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.37155/2717-5669-0401-28, pmid=null, pmcid=null, year=2023, volume=4, issue=1, pageStart=83, pageEnd=85, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=郭亚梅, 蒋凌燕, 段正凡, journalName=国际全科医学, refType=null, unstructuredReference=郭亚梅,蒋凌燕,段正凡. 乳腺钼靶X线摄影诊断乳腺癌的应用价值分析[J]. 国际全科医学,2023.4(1):83-85., articleTitle=乳腺钼靶X线摄影诊断乳腺癌的应用价值分析, refAbstract=null), Reference(id=1322934497100050537, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.37155/2717-5669-0401-28, pmid=null, pmcid=null, year=2023, volume=4, issue=1, pageStart=83, pageEnd=85, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=GAO Y M, JIANG L Y, DUAN Z F, journalName=Int J Gen Med, refType=null, unstructuredReference=GAO Y M,JIANG L Y,DUAN Z F,et al. The value of mammography in the diagnosis of breast cancer[J]. Int J Gen Med,2023.4(1):83-85., articleTitle=The value of mammography in the diagnosis of breast cancer, refAbstract=null), Reference(id=1322934498727440490, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1016/j.eclinm.2023.102001, pmid=null, pmcid=null, year=2023, volume=60, issue=null, pageStart=102001, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=LIAO J W, GUI Y, LI Z L, journalName=EClinicalMedicine, refType=null, unstructuredReference=LIAO J W,GUI Y,LI Z L,et al. Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population:a retrospective,multicentre,cohort study[J]. EClinicalMedicine,2023,60:102001., articleTitle=Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population:a retrospective,multicentre,cohort study, refAbstract=null), Reference(id=1322934498790355051, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1016/j.artmed. 2023.102547, pmid=null, pmcid=null, year=2023, volume=140, issue=null, pageStart=102547, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=6, authorNames=FARAH L, DAVAZE-SCHNEIDER J, MARTIN T, journalName=Artif Intell Med, refType=null, unstructuredReference=FARAH L,DAVAZE-SCHNEIDER J,MARTIN T,et al. Are current clinical studies on artificial intelligence-based medical devices comprehensive enough to support a full health technology assessment:A systematic review[J]. Artif Intell Med,2023,140:102547., articleTitle=Are current clinical studies on artificial intelligence-based medical devices comprehensive enough to support a full health technology assessment:A systematic review, refAbstract=null), Reference(id=1322934498853269612, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.3390/jimaging9050095, pmid=null, pmcid=null, year=2023, volume=9, issue=5, pageStart=95, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=MRAČKO A, VANOVČANOVÁ L, CIMRÁK I, journalName=J Imaging, refType=null, unstructuredReference=MRAČKO A,VANOVČANOVÁ L,CIMRÁK I. Mammography datasets for neural networks-survey[J]. J Imaging,2023,9(5):95., articleTitle=Mammography datasets for neural networks-survey, refAbstract=null), Reference(id=1322934498928767085, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1007/s00779-021-01598-1, pmid=null, pmcid=null, year=2023, volume=27, issue=3, pageStart=1233, pageEnd=1244, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=KIM C M, CHUNG K, PARK R C, journalName=Pers Ubiquitous Comput, refType=null, unstructuredReference=KIM C M,CHUNG K,PARK R C. Anomaly detection model of mammography using YOLOv4-based histogram[J]. Pers Ubiquitous Comput,2023,27(3):1233-1244., articleTitle=Anomaly detection model of mammography using YOLOv4-based histogram, refAbstract=null), Reference(id=1322934498995875950, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1007/s00330-021-07796-y, pmid=null, pmcid=null, year=2021, volume=31, issue=9, pageStart=6929, pageEnd=6937, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=LEE S E, HAN K, KIM E K, journalName=Eur Radiol, refType=null, unstructuredReference=LEE S E,HAN K,KIM E K. Application of artificial intelligence-based computer-assisted diagnosis on synthetic mammograms from breast tomosynthesis:comparison with digital mammograms[J]. Eur Radiol,2021,31(9):6929-6937., articleTitle=Application of artificial intelligence-based computer-assisted diagnosis on synthetic mammograms from breast tomosynthesis:comparison with digital mammograms, refAbstract=null), Reference(id=1322934499071373423, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1016/j.clbc.2022.12.016, pmid=null, pmcid=null, year=2023, volume=23, issue=3, pageStart=e112, pageEnd=e121, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=WANG Y Q, TANG L, CHEN P P, journalName=Clin Breast Cancer, refType=null, unstructuredReference=WANG Y Q,TANG L,CHEN P P,et al. The role of a deep learning-based computer-aided diagnosis system and elastography in reducing unnecessary breast lesion biopsies[J]. Clin Breast Cancer,2023,23(3):e112-e121., articleTitle=The role of a deep learning-based computer-aided diagnosis system and elastography in reducing unnecessary breast lesion biopsies, refAbstract=null), Reference(id=1322934499130093680, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1007/s10278-023-00836-7, pmid=null, pmcid=null, year=2023, volume=36, issue=4, pageStart=1541, pageEnd=1552, url=null, language=null, rfNumber=10, rfOrder=11, authorNames=SIVIENGPHANOM S, GANDOMKAR Z, LEWIS S J, journalName=J Digit Imag, refType=null, unstructuredReference=SIVIENGPHANOM S,GANDOMKAR Z,LEWIS S J,et al. Global radiomic features from mammography for predicting difficult-to-interpret normal cases[J]. J Digit Imag,2023,36(4):1541-1552., articleTitle=Global radiomic features from mammography for predicting difficult-to-interpret normal cases, refAbstract=null), Reference(id=1322934499209785457, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1117/12.2216767, pmid=null, pmcid=null, year=2016, volume=9785, issue=1, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=11, rfOrder=12, authorNames=RABIDAS R, MIDYA A, SADHU A, journalName=null, refType=null, unstructuredReference=RABIDAS R,MIDYA A,SADHU A,et al. Benign-malignant mass classification in mammogram using edge weighted local texture features[C]. Med Ima 2016:Comput Aided Diag-SPIE,2016,9785(1x):1-6., articleTitle=Benign-malignant mass classification in mammogram using edge weighted local texture features, refAbstract=null), Reference(id=1322934499285282930, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.3390/diagnostics 13091618, pmid=null, pmcid=null, year=2023, volume=13, issue=9, pageStart=1618, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=13, authorNames=REHMAN S U, KHAN M A, MASOOD A, journalName=Diagnostics, refType=null, unstructuredReference=REHMAN S U,KHAN M A,MASOOD A,et al. BRMI-net:deep learning features and flower pollination-controlled regula falsi-based feature selection framework for breast cancer recognition in mammography images[J]. Diagnostics,2023,13(9):1618., articleTitle=BRMI-net:deep learning features and flower pollination-controlled regula falsi-based feature selection framework for breast cancer recognition in mammography images, refAbstract=null), Reference(id=1322934499369169011, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1038/sdata.2017.177, pmid=null, pmcid=null, year=2017, volume=4, issue=null, pageStart=170177, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=14, authorNames=LEE R S, GIMENEZ F, HOOGI A, journalName=Sci Data, refType=null, unstructuredReference=LEE R S,GIMENEZ F,HOOGI A,et al. A curated mammography data set for use in computer-aided detection and diagnosis research[J]. Sci Data,2017,4:170177., articleTitle=A curated mammography data set for use in computer-aided detection and diagnosis research, refAbstract=null), Reference(id=1322934499465638004, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1038/s41598-019-48995-4, pmid=null, pmcid=null, year=2019, volume=9, issue=null, pageStart=12495, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=15, authorNames=SHEN L, MARGOLIES L R, ROTHSTEIN J H, journalName=Sci Rep, refType=null, unstructuredReference=SHEN L,MARGOLIES L R,ROTHSTEIN J H,et al. Deep learning to improve breast cancer detection on screening mammography[J]. Sci Rep,2019,9:12495., articleTitle=Deep learning to improve breast cancer detection on screening mammography, refAbstract=null), Reference(id=1322934499541135477, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1016/j.acra.2011.09.014, pmid=null, pmcid=null, year=2012, volume=19, issue=2, pageStart=236, pageEnd=248, url=null, language=null, rfNumber=15, rfOrder=16, authorNames=MOREIRA I C, AMARAL I, DOMINGUES I, journalName=Acad Radiol, refType=null, unstructuredReference=MOREIRA I C,AMARAL I,DOMINGUES I,et al. INbreast:toward a full-field digital mammographic database[J]. Acad Radiol,2012,19(2):236-248., articleTitle=INbreast:toward a full-field digital mammographic database, refAbstract=null), Reference(id=1322934499599855734, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.1007/978-94-011-5318-8_75, pmid=null, pmcid=null, year=1998, volume=null, issue=null, pageStart=457, pageEnd=460, url=null, language=null, rfNumber=16, rfOrder=17, authorNames=HEATH M, BOWYER K, KOPANS D, journalName=Current status of the digital database for screening mammography, refType=null, unstructuredReference=HEATH M,BOWYER K,KOPANS D,et al. Current status of the digital database for screening mammography[M]. Dordrecht:Springer Netherlands,1998:457-460., articleTitle=null, refAbstract=null), Reference(id=1322934499666964599, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=null, pmid=null, pmcid=null, year=1994, volume=null, issue=null, pageStart=375, pageEnd=378, url=null, language=null, rfNumber=17, rfOrder=18, authorNames=SUCKLING J, PARKER J, ASTLEY S, journalName=null, refType=null, unstructuredReference=SUCKLING J,PARKER J,ASTLEY S,et al. The Mammographic Image Analysis Society digital mammogram database[C]. Int Congr Ser,1994:375-378. https://www.repository.cam.ac.uk/handle/1810/250394., articleTitle=The Mammographic Image Analysis Society digital mammogram database, refAbstract=null), Reference(id=1322934499725684856, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.3969/j.issn.1674-5671.2020.04.19, pmid=null, pmcid=null, year=2020, volume=12, issue=4, pageStart=469, pageEnd=474, url=null, language=null, rfNumber=18, rfOrder=19, authorNames=彭芳芳, 沈坤炜, journalName=中国癌症防治杂志, refType=null, unstructuredReference=彭芳芳,沈坤炜. 中西方女性乳腺密度与乳腺癌发病关系的研究进展[J]. 中国癌症防治杂志,2020,12(4):469-474., articleTitle=中西方女性乳腺密度与乳腺癌发病关系的研究进展, refAbstract=null), Reference(id=1322934499801182329, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.3969/j.issn.1674-5671.2020.04.19, pmid=null, pmcid=null, year=2020, volume=12, issue=4, pageStart=469, pageEnd=474, url=null, language=null, rfNumber=18, rfOrder=20, authorNames=PENG F F, SHEN K W, journalName=Chin J Oncol Prev Treat, refType=null, unstructuredReference=PENG F F,SHEN K W. Research progress on the relationship between breast density and breast cancer in Chinese and western women[J]. Chin J Oncol Prev Treat,2020,12(4):469-474., articleTitle=Research progress on the relationship between breast density and breast cancer in Chinese and western women, refAbstract=null), Reference(id=1322934499851513978, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.27157/d.cnki.ghzku.2020.001367, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=8, pageEnd=36, url=null, language=null, rfNumber=19, rfOrder=21, authorNames=董誉, journalName=null, refType=null, unstructuredReference=董誉. 乳腺钼靶图像中的肿块良恶性分类[D]. 武汉:华中科技大学,2020:8-36., articleTitle=乳腺钼靶图像中的肿块良恶性分类, refAbstract=null), Reference(id=1322934499918622843, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.27157/d.cnki.ghzku.2020.001367, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=8, pageEnd=36, url=null, language=null, rfNumber=19, rfOrder=22, authorNames=DONG Y, journalName=null, refType=null, unstructuredReference=DONG Y. Classification of benign and malignant masses in mammography[D]. Wuhan:Huazhong University of Science and Technology,2020:8-36., articleTitle=Classification of benign and malignant masses in mammography, refAbstract=null), Reference(id=1322934499973148796, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.3760/cma.j.cn112271-20240205-00045, pmid=null, pmcid=null, year=2024, volume=44, issue=4, pageStart=278, pageEnd=285, url=null, language=null, rfNumber=20, rfOrder=23, authorNames=薛珂, 徐辉, 岳保荣, journalName=中华放射医学与防护杂志, refType=null, unstructuredReference=薛珂,徐辉,岳保荣,等. 我国女性乳腺体积密度及相关乳房特征定量研究[J]. 中华放射医学与防护杂志,2024,44(4):278-285., articleTitle=我国女性乳腺体积密度及相关乳房特征定量研究, refAbstract=null), Reference(id=1322934500052840573, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, doi=10.3760/cma.j.cn112271-20240205-00045, pmid=null, pmcid=null, year=2024, volume=44, issue=4, pageStart=278, pageEnd=285, url=null, language=null, rfNumber=20, rfOrder=24, authorNames=XUE K, XU H, YUE B R, journalName=Chin J Radiol Med Prot, refType=null, unstructuredReference=XUE K,XU H,YUE B R,et al. Quantitative study on female breast bulk density and related breast characteristics in China[J]. Chin J Radiol Med Prot,2024,44(4):278-285., articleTitle=Quantitative study on female breast bulk density and related breast characteristics in China, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)]), AuthorCompany(id=1322934491198664736, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=2, ext=[AuthorCompanyExt(id=1322934491211247649, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491198664736, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Department of Digital Medicine,Faculty of Biomedical Engineering and Imaging Medicine,Army Medical University (Third Military Medical University),Chongqing, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491219636258, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491198664736, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2陆军军医大学(第三军医大学)生物医学工程与影像医学系:数字医学教研室,重庆)]), AuthorCompany(id=1322934491282550819, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=3, ext=[AuthorCompanyExt(id=1322934491299328036, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491282550819, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Department of Medical Engineering, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491311910949, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491282550819, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3陆军特色医学中心(第三军医大学大坪医院)医学工程科,重庆)])], figs=[ArticleFig(id=1322934495707541593, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=EN, label=null, caption=null, figureFileSmall=4dk05WjW45EdGQiT5I3kxA==, figureFileBig=EYLCbGoA1uTMh5ZPtzpWqA==, tableContent=null), ArticleFig(id=1322934495791427674, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=CN, label=图1, caption=研究总体方案设计流程图, figureFileSmall=4dk05WjW45EdGQiT5I3kxA==, figureFileBig=EYLCbGoA1uTMh5ZPtzpWqA==, tableContent=null), ArticleFig(id=1322934495959199835, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=EN, label=null, caption=null, figureFileSmall=fskPdvO7ysvBjXgCMVZRBA==, figureFileBig=IHY8fyzFMMVrHQcqLRbrbQ==, tableContent=null), ArticleFig(id=1322934496034697308, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=CN, label=图2, caption=滑动窗口调窗流程, figureFileSmall=fskPdvO7ysvBjXgCMVZRBA==, figureFileBig=IHY8fyzFMMVrHQcqLRbrbQ==, tableContent=null), ArticleFig(id=1322934496110194781, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=EN, label=null, caption=null, figureFileSmall=MYW/jYoj6izmeyziTh+CEA==, figureFileBig=9juNdzuS2H/pAR3OfneCFg==, tableContent=null), ArticleFig(id=1322934496177303646, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=CN, label=图3, caption=滑动窗口调窗机制下同一钼靶影像的成像效果对比

A:默认窗(486/972 WL/WW);B:动态获取最优模型窗宽窗位下的调窗(485/485 WL/WW)

, figureFileSmall=MYW/jYoj6izmeyziTh+CEA==, figureFileBig=9juNdzuS2H/pAR3OfneCFg==, tableContent=null), ArticleFig(id=1322934496248606815, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=EN, label=null, caption=null, figureFileSmall=3NVADH+yGse4O/TdPEEpQA==, figureFileBig=8vdSDNYMb5zdOzH+IC6BDw==, tableContent=null), ArticleFig(id=1322934496315715680, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=CN, label=图4, caption=乳腺钼靶图像良恶性分类与肿块目标检测系统设计效果

A:以国际公开数据集图像为例选用模型一 图中标记为malignant;B:以中国人群图像为例选用模型三 图中标记为benign

, figureFileSmall=3NVADH+yGse4O/TdPEEpQA==, figureFileBig=8vdSDNYMb5zdOzH+IC6BDw==, tableContent=null), ArticleFig(id=1322934496378630241, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
序号测试集模型准确度精度灵敏度F1值AUC
1CBIS-DSM模型一0.920.910.910.910.98
2DW-CBMD模型一0.500.540.520.520.51
3WL-CBMD模型一0.510.530.520.520.52
4DW-CBMD模型二0.770.790.770.760.75
5WL-CBMD模型三0.800.820.800.800.89
), ArticleFig(id=1322934496466710626, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=CN, label=表1, caption=

不同训练数据集或不同训练阶段获得的分类模型在各类测试集上的性能比较

, figureFileSmall=null, figureFileBig=null, tableContent=
序号测试集模型准确度精度灵敏度F1值AUC
1CBIS-DSM模型一0.920.910.910.910.98
2DW-CBMD模型一0.500.540.520.520.51
3WL-CBMD模型一0.510.530.520.520.52
4DW-CBMD模型二0.770.790.770.760.75
5WL-CBMD模型三0.800.820.800.800.89
), ArticleFig(id=1322934496542208099, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
方法准确度F1值
公开数据集组图像训练0.848 60.847 3
公开数据集组图像增强0.888 10.886 4
二阶段迁移学习0.920 20.919 7
DW-CBMD组图像训练0.754 10.752 0
DW-CBMD组图像增强0.756 40.753 1
二阶段迁移学习0.770 10.766 4
WL-CBMD组图像训练0.791 20.783 3
WL-CBMD组图像增强0.804 50.800 8
二阶段迁移学习0.809 00.807 3
), ArticleFig(id=1322934496617705572, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, language=CN, label=表2, caption=

各类图像数据集在不同预处理方法下的消融实验结果比较

, figureFileSmall=null, figureFileBig=null, tableContent=
方法准确度F1值
公开数据集组图像训练0.848 60.847 3
公开数据集组图像增强0.888 10.886 4
二阶段迁移学习0.920 20.919 7
DW-CBMD组图像训练0.754 10.752 0
DW-CBMD组图像增强0.756 40.753 1
二阶段迁移学习0.770 10.766 4
WL-CBMD组图像训练0.791 20.783 3
WL-CBMD组图像增强0.804 50.800 8
二阶段迁移学习0.809 00.807 3
)], 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.2097-0927.202407001, detailUrlEn=https://castjournals.cast.org.cn/joweb/ljjydxxb/EN/10.16016/j.2097-0927.202407001, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ljjydxxb/CN/PDF/10.16016/j.2097-0927.202407001, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ljjydxxb/EN/PDF/10.16016/j.2097-0927.202407001, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1736870400000, fullTextJson=null, articleText=null, reference=null)
收藏切换
适应中国人群的乳腺钼靶X线图像分类辅助系统设计
收藏切换
PDF下载
孙常晋 1 , 童飞 2 , 吴毅 3 , 王雨婷 1 , 罗俊捷 1 , 龚滟 1 , 邱明国 1 , 乔梁 1
陆军军医大学学报 | 生物医学工程 2025,47(1): 92-99
收起
收藏切换
陆军军医大学学报 |生物医学工程 2025 , 47 (1) : 92 -99
适应中国人群的乳腺钼靶X线图像分类辅助系统设计
全屏
[Author(id=1322934491387408423, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934491500654633, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491387408423, language=EN, stringName=Changjin SUN, firstName=Changjin, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934491571957802, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491387408423, language=CN, stringName=孙常晋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])]), Author(id=1322934491639066668, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934491718758446, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491639066668, language=EN, stringName=Fei TONG, firstName=Fei, middleName=null, lastName=TONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Department of Digital Medicine,Faculty of Biomedical Engineering and Imaging Medicine,Army Medical University (Third Military Medical University),Chongqing, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934491802644527, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491639066668, language=CN, stringName=童飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2陆军军医大学(第三军医大学)生物医学工程与影像医学系:数字医学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491198664736, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=2, ext=[AuthorCompanyExt(id=1322934491211247649, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491198664736, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Department of Digital Medicine,Faculty of Biomedical Engineering and Imaging Medicine,Army Medical University (Third Military Medical University),Chongqing, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491219636258, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491198664736, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2陆军军医大学(第三军医大学)生物医学工程与影像医学系:数字医学教研室,重庆)])]), Author(id=1322934491865559089, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934491936862259, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491865559089, language=EN, stringName=Yi WU, firstName=Yi, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Department of Medical Engineering, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934491991388212, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934491865559089, language=CN, stringName=吴毅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3陆军特色医学中心(第三军医大学大坪医院)医学工程科,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491282550819, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=3, ext=[AuthorCompanyExt(id=1322934491299328036, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491282550819, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Department of Medical Engineering, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491311910949, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491282550819, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3陆军特色医学中心(第三军医大学大坪医院)医学工程科,重庆)])]), Author(id=1322934492050108470, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934492117217336, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492050108470, language=EN, stringName=Yuting WANG, firstName=Yuting, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934492192714809, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492050108470, language=CN, stringName=王雨婷, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])]), Author(id=1322934492259823675, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934492335321149, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492259823675, language=EN, stringName=Junjie LUO, firstName=Junjie, middleName=null, lastName=LUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934492419207230, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492259823675, language=CN, stringName=罗俊捷, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])]), Author(id=1322934492494704704, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, 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=1322934492570202178, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492494704704, language=EN, stringName=Yan GONG, firstName=Yan, middleName=null, lastName=GONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934492633116739, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934492494704704, language=CN, stringName=龚滟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])]), Author(id=1322934494302449733, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, orderNo=6, 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=1322934494398918727, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934494302449733, language=EN, stringName=Mingguo QIU, firstName=Mingguo, middleName=null, lastName=QIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934494478610505, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934494302449733, language=CN, stringName=邱明国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])]), Author(id=1322934494566690891, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, orderNo=7, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=bobq310@tmmu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322934494658965581, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934494566690891, language=EN, stringName=Liang QIAO, firstName=Liang, middleName=null, lastName=QIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322934494734463054, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, authorId=1322934494566690891, language=CN, stringName=乔梁, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322934491123167261, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, xref=1, ext=[AuthorCompanyExt(id=1322934491135750174, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China), AuthorCompanyExt(id=1322934491144138783, tenantId=1146029695717560320, journalId=1319373162502258839, articleId=1322934488413646862, companyId=1322934491123167261, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆)])])]
孙常晋1, 童飞2, 吴毅3, 王雨婷1, 罗俊捷1, 龚滟1, 邱明国1, 乔梁1
作者信息
  • 1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆
  • 2陆军军医大学(第三军医大学)生物医学工程与影像医学系:数字医学教研室,重庆
  • 3陆军特色医学中心(第三军医大学大坪医院)医学工程科,重庆
通讯作者:
乔梁,E-mail:
QIAO Liang,E-mail:
Design of a mammography X-ray image classification assistant system adapted to Chinese population
Changjin SUN1, Fei TONG2, Yi WU3, Yuting WANG1, Junjie LUO1, Yan GONG1, Mingguo QIU1, Liang QIAO1
Affiliations
  • 1Department of Medical Imaging, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China
  • 2Department of Digital Medicine,Faculty of Biomedical Engineering and Imaging Medicine,Army Medical University (Third Military Medical University),Chongqing, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China
  • 3Department of Medical Engineering, Army Medical Center of PLA/Daping Hospital of Third Military Medical University,Chongqing,China
出版时间: 2025-01-15 doi: 10.16016/j.2097-0927.202407001
文章导航
收藏切换
目的

构建适应中国人群的乳腺钼靶图像分类辅助系统,探讨人工智能技术在国内辅助乳腺癌早期筛查的潜力。

方法

为复现当前文献中的主流深度学习方法,利用乳腺X线筛查数字数据库子集(curated breast imaging subset of digital database for screening mammography,CBIS-DDSM)、乳房X线图像分析学会数据库(mammographic image analysis society database,MIAS)等国际公开数据集分别进行模型训练,并在华教科技有限公司提供的中国人群乳腺钼靶图像数据集(Chinese breast mammography dataset,CBMD)上进行测试和模型性能比较;针对中国人群数据在公开数据集训练模型性能测试不理想的问题,结合中国人群数据特点,提出基于滑动窗口调窗机制的优化策略,设计二阶段迁移学习方法,以提升模型的整体性能,并进行系统研发。

结果

使用滑动窗口调窗机制及二阶段迁移学习后的CBMD训练模型,以中国人群数据集为测试集,其准确度从默认窗口下公开数据集训练模型的0.50提升至0.80,精度从0.54提升至0.82,灵敏度从0.52提升至0.80,F1值从0.52提升至0.80,AUC值从0.51提升至0.89。

结论

本研究引入滑动窗口调窗机制和二阶段迁移学习策略,显著提升了乳腺钼靶图像分类模型在中国人群数据集上的性能,初步达到适应中国人群的乳腺钼靶图像辅助分类的目的。

乳腺钼靶  /  深度学习  /  X射线  /  计算机辅助
Objective‍

To construct a mammography image classification assistant system suitable for Chinese population,and explore the potential of artificial intelligence technology to assist early screening of breast cancer in China.

Methods‍

Curated breast imaging subset of digital database for screening mammography (CBIS-DDSM),Mammographic image analysis society database (MIAS) and other international open datasets were used to conduct model training respectively in order to reproduce the mainstream in-depth learning methods in the current literature. The model was also tested on the Chinese breast mammography database (CBMD) provided by Huajiao Technology Co.,Ltd,and the performance was compared. Aiming at the problem that the Chinese population data are not ideal in the performance test of the open dataset training model,an optimization strategy based on the sliding window adjustment mechanism was implemented in combination with the characteristics of Chinese population data. Then a two-stage migration learning method was designed to improve the overall performance of the model,and then development of our system was carried out.

Results‍

With the sliding window adjustment mechanism and the CBMD training model after two-stage transfer learning,the accuracy of our developed system was improved from 0.50 of the open datasets to 0.80,precision from 0.54 to 0.82,sensitivity from 0.52 to 0.80,F1 value from 0.52 to 0.80,and AUC value from 0.51 to 0.89 based on the Chinese population dataset as the test set.

Conclusion‍

Through the introduction of sliding window adjustment mechanism and two-stage migration learning strategy,the performance of the breast molybdenum target image classification model has been significantly improved in the Chinese population dataset,and our system primarily achieves the purpose of assisting the classification of breast molybdenum target images for the Chinese population.

mammography  /  deep learning  /  X-Ray  /  computer assistance
孙常晋, 童飞, 吴毅, 王雨婷, 罗俊捷, 龚滟, 邱明国, 乔梁. 适应中国人群的乳腺钼靶X线图像分类辅助系统设计. 陆军军医大学学报, 2025 , 47 (1) : 92 -99 . DOI: 10.16016/j.2097-0927.202407001
Changjin SUN, Fei TONG, Yi WU, Yuting WANG, Junjie LUO, Yan GONG, Mingguo QIU, Liang QIAO. Design of a mammography X-ray image classification assistant system adapted to Chinese population[J]. Journal of Army Medical University, 2025 , 47 (1) : 92 -99 . DOI: 10.16016/j.2097-0927.202407001
乳腺癌[1-2]是全球女性常见的恶性肿瘤,全球每年约有200万例新诊病例。预防和早期筛查对于乳腺癌的有效治疗至关重要。乳腺钼靶[3] 是一种使用X射线技术来检查乳房的方法,具有低辐射剂量、非侵入性等优点。相比于一些高端筛查技术如磁共振成像(magnetic resonance imaging,MRI),乳腺钼靶检查的费用相对较低且检查过程相对简单,一直是欧美国家进行乳腺癌早期检测的主要工具。近年来,基于人工智能(artificial intelligence,AI)[4-7]技术支持下的计算机辅助诊断(computer-aided diagnosis,CAD)[8-10]可进一步提高乳腺癌乳腺钼靶诊断准确率,极大地提高了乳腺癌的早期检出率。
目前,基于AI的乳腺癌乳腺钼靶辅助诊断主要有2种思路:基于感兴趣区域(region of interest,ROI)的肿块分类以及基于全图的乳腺癌良恶性分类。基于目标检测的肿块分类算法,需要对训练数据的每个肿块进行标注之后再进行训练。为提升ROI区域的训练质量,RABIDAS等[11]提出一种二值模式,用以区分明暗部,提升边缘特征提取质量,在数字乳腺X线摄影软件的数字数据库(digital database for digital mammography software,DDSM)上的AUC高达0.982,然而准确度的攀升背后是大量的影像数据需要人工进行ROI区域的截取或标注。基于全图的良恶分类算法其优势是无需对训练数据进行手工标注,但为应对识别性能的挑战,REHMAN等[12]提出一种结合深度学习和花朵授粉算法优化的新框架,在乳腺X线筛查数字数据库子集(curated breast imaging subset of digital database for screening mammography,CBIS-DDSM)[13]数据集上达到了93.8%的准确率。SHEN等[14]使用全卷积网络的方法分别在DDSM、全领域数字乳腺X线数据库(a full-field digital mammographic database,INbreast)[15]上进行测试,在DDSM上的最佳AUC可以达到0.88。
但是,上述工作主要依托国际公共数据集,而现有的国际公共数据集[16]如CBIS-DDSM、INbreast、乳房X线图像分析学会数据库(mammographic image analysis society database,MIAS)[17]等主要来自欧美人种,与中国人群相比在乳腺体积、组织密度等方面存在较大差异[18],上述相关研究成果难以直接适用于中国人群,且国内的相关文献极少针对中国人群的应用效果进行研究。基于此,本研究通过将中国人群乳腺钼靶图像数据集(Chinese breast mammography dataset,CBMD),与现有研究和公共数据集结合,探索适用于中国人群的乳腺钼靶辅助诊断方法,并设计研发适应中国人群特点的乳腺钼靶X线图像分类辅助系统,以期缩小与国外在乳腺钼靶筛查应用规模上的差距。
本研究共纳入3组数据集,国际公开数据集MIAS、CBIS-DDSM以及中国数据集CBMD。其中,MIAS数据集包含207张良性图像,85张恶性图像;CBIS-DDSM数据集包含良性图像数量为227张,恶性图像数量1 365张;中国人群乳腺钼靶图像数据集CBMD来自重庆华教科技公司提供的医学影像病例数据库系统,均进行了脱敏处理,经整理包含乳腺癌病例良性23例,恶性31例,根据诊断意见对数据集进行分类,最终得到分类数据集良性142张,恶性72张。
本研究主要分为3个步骤,总体方案设计流程见图1。
通过使用MIAS数据集以及CBIS-DDSM数据集的两阶段迁移学习,构建出一个通用的分类模型(模型一),同时该模型也作为适应中国人群的乳腺数据集的预训练模型。
设计滑动窗口机制的调窗技术,以更好区分乳腺组织密度与肿块密度,借助第一步使用国际公开数据集的良恶分类研究的预训练模型完成针对中国人群的两阶段迁移学习,构建模型二(未包含滑动窗口机制)和最终模型三。
将前两步获取的训练模型进行系统化设计,初步构建操作简便的桌面应用软件,并进行功能验证。
选用MIAS作为第一阶段的全图良恶性分类训练数据集。针对MIAS样本量较少的情况,进一步选用CBIS-DDSM作为第二阶段的训练集完成全图良恶性分类。并通过数据预处理、样本均衡等方法提升模型的训练质量。
为得到更好的训练效果,MIAS和CBIS-DDSM数据集进行了相同的预处理。通过高斯滤波降噪,使用局部直方图均衡化提升其对比度,使乳腺内部纹理更为清晰。同时,在样本均衡方面,MIAS肿块病例数据集中良性的数量为207张,恶性的数量85张,CBIS-DDSM肿块病例数据集中良性的数量为227张,恶性的数量1 365张,样本均极度不均衡,如直接进行训练容易导致模型过拟合。故使用数据增强的方法,对良性图片分别做了拉伸、模糊、放缩、旋转、平移5种变换,使CBIS-DDSM的良性数据集数量增长至1 362张,与恶性数据集数量1 365张基本一致;使MIAS的恶性数据量增长至170张,与良性数据量207张基本一致。总体保证样本分布均匀。
在从MIAS到CBIS-DDSM的二阶段迁移学习中,首先使用ResNet50的官方预训练权重对MIAS数据集进行训练,在训练完成得到新的预训练模型后,进一步训练CBIS-DDSM肿块病例数据集。由于MIAS数据集的成像设备与CBIS-DDSM相近,因此模型可以从不同数据集中学习到更多特征,在一定程度上弥补CBIS-DDSM数据集中良性组织特征较少、MIAS恶性组织特征较少的问题,从而提升模型性能与模型泛化能力。训练完成后,即得到使用国际公开数据集的乳腺钼靶良恶分类模型(模型一),并将CBMD作为测试集进行比较测试,评估该模型是否适用于中国人群乳腺癌的分类。
中国人群的乳腺组织密度相较于欧美人群更高,在钼靶影像中通常表现为较大面积的白色区域,而乳腺癌病灶同样以白色区域呈现。相比之下,欧美人群的乳房尺寸和体积较大,乳腺组织相对松散,更易显现病变的具体位置和边界。这一特性使得中国人群的钼靶影像在组织定位和识别中更加困难。
针对中国人群乳腺钼靶中组织密度较高的问题,本研究提出使用DICOM医学影像特有的调窗方法,以增大不同区域的密度差异。调窗技术是一种医学影像处理方法,将12~16位的像素深度映射至传统的8位灰度图,用于有针对性的显影和图像显示。相比于传统8位灰度图通过调整灰度直方图比例来改变图像亮度和对比度的方法,调窗技术可以更好地利用医学图像12~16位灰度级的成像特点,找寻更多的医学图像结构细节,并显示出不同区域的密度差别。在乳腺钼靶的检查中,乳腺组织的密度低于肿块和其他异常病变区域,使用适当的窗宽和窗位可以突出显示病变区域,使模型更容易发现和定位病灶特征,提高疾病检测和诊断的精度和准确性。
本研究设计了一种“滑动窗口调窗机制”的调窗方法,具体流程见图2。其主要思想是:定义初始的窗宽和窗位值,并指定单次窗口移动步长大小。将每次移动步长下的滑动窗口的数据输入到模型,采用ResNet50进行100轮的训练测试。将不同步长的训练结果进行汇总统计,找出AUC值最大的模型所对应的窗宽(WW)和窗位(WL)。
图3展示了同一例钼靶影像中,使用默认窗口与本方法获得的最佳窗口的成像效果的对比。最佳窗口下,红色框标记的肿块和斑点状钙化灶与周围组织的区分度更加明显。故本研究对中国人群数据集CBMD按照“滑动窗口调窗机制”进行统一预处理,作为新的训练集,在基于“1.3国际公开数据集的乳腺钼靶良恶分类”模型基础上,通过ResNet50进行二阶段迁移训练学习,得到适用于中国人群的乳腺钼靶全图良恶分类的最终训练模型(模型三)。同时,使用相同方法训练不包括滑动调窗机制的模型二,用于对滑动窗口调窗机制作用的对照实验。
系统设计旨在将深度学习算法与桌面软件的研发相结合,构建针对中国人群乳腺钼靶图像分类的辅助系统,方便实验验证。主要包括开发环境、技术选型、功能模块及其人机交互设计。
本系统使用 Python 3.8 作为主要编程语言,采用 ResNet50 作为全图良恶性分类的模型训练框架,并基于 PyTorch 完成模型的训练与部署。
模型的训练基于Windows11操作系统,在配备 16 GB显存的GPU RTX 3060上,选用ResNet50框架按照1.3~1.4的方法进行模型的迁移训练。各阶段模型训练中,数据集MIAS、CBIS-DDSM以及CBMD均按照7∶3的比例划分训练集和测试集,测试指标包括精度、查准率、灵敏度、F1值和AUC值。
在两阶段的迁移训练过程中,第一阶段使用ResNet50的官方预训练模型(初始为1 000分类,移除初始全连接层,添加二分类全连接层),总体迭代次数为100次,批数据大小(Batch size)为64,分类模型学习率设置为1e-3,使用的优化器为Adam;第二阶段在第一阶段获得的预训练模型基础上进行迁移学习,总体迭代次数为500次,批数据大小(Batch size)为64,分类模型学习率设置为1e-3,使用的优化器为Adam。同时结合 PyQt5 实现界面设计与功能开发。
该模块主要负责对乳腺钼靶图像进行良性与恶性分类。通过深度学习算法模型ResNet50自动检测和识别医学图像,提供分类结果与置信度。
该模块主要用于向用户介绍本软件所使用模型的数据集来源,并为研究人员提供标准化医学图像及数据集官网链接,便于数据的共享、交流、调用与复用。目前支持的数据集包括 CBIS-DDSM、MIAS、INbreast 和中国人群乳腺钼靶数据集CBMD。随着数据集的不断完善,系统将持续更新并纳入更多资源。
该模块主要负责系统中用户的注册、登录和密码修改,为医生、工程师及其它系统用户提供便捷的使用体验和管理操作。
登录系统后,即进入分类与检测页面(图4)。图4A为适应公开数据集全图良恶分类系统测试结果,通过点击文件夹图标选择钼靶图片,通过文件夹图标下侧的下拉单选择分类模型(模型一、二、三)后,页面右侧即显示分类结果;图4B为适应中国人群数据集全图良恶分类结果。除良恶分类任务外,本研究还在公开数据集INbreast基础上结合YOLOv5模型训练了一种肿块目标检测模型,并将其集成到系统中,作为良恶性分类后,辅助操作者快速定位目标肿块的参考(图4)。
模型一为1.3使用国际公开数据集完成的最终分类模型;模型二为1.4使用中国人群数据集CBMD默认窗口(default window CBMD,DW-CBMD)获得的最终分类模型(未使用1.4.2滑动窗口调窗机制);模型三为“1.4.2滑动窗口调窗机制的设计”后获得最佳窗口(window leveling CBMD,WL-CBMD)后得到的适用于中国人群的乳腺钼靶全图良恶分类的最终模型。本研究分别使用CBIS-DDSM、DW-CMBD、WL-CBMD的测试集对3种模型进行性能测试,见表1。
表1中,序号2、3处使用公开数据集训练出的模型一无论是在调窗前还是调窗后,其针对中国人群数据集的AUC仅为0.51、0.52,远不及序号1处完全使用国外公共数据集的测试结果。序号5使用调窗后的中国人群数据集训练获取的模型三,其针对中国人群数据集的AUC值相比序号2提升了0.38,进一步证实了单纯使用以欧美人群为主体的国际公开数据集训练的模型不适用于中国人群乳腺钼靶分类。
序号4处使用中国人群数据集默认窗训练出的模型二,各项性能指标优于序号2~3,但显著低于序号5处经过滑动窗口机制调窗得到的最优效果模型三,模型三的AUC值相较于模型二的AUC值提升了0.14。可见本研究提出的滑动窗口机制调窗在中国人群数据特征的识别方面有着明显的优势。
为观察图像增强和二阶段迁移学习的效果,并对每一阶段结果进行比较,本研究分别对公开数据集组、中国人群乳腺钼靶图像WL-CBMD调窗组和DW-CBMD默认窗组进行了消融实验,表2展示了乳腺分类模型在中国人群乳腺钼靶图像数据集上对本研究提到方法进行消融实验的结果。
其中,公开数据集组采用“1.3基于国际公开数据集的乳腺钼靶”全图良恶分类训练方法,分别对训练集进行原数据训练和图像增强后训练;DW-CBMD组采用“1.4适用于中国人群的乳腺钼靶全图良恶分类”训练方法,排除滑动调窗机制后,分别对DW-CBMD训练集进行原数据训练和图像增强后训练;WL-CBMD组采用“1.4适用于中国人群的乳腺钼靶全图良恶分类”的完整训练方法,分别对WL-CBMD训练集进行原数据训练和图像增强后训练。并分别针对上述3组数据集各自方法进行二阶段迁移学习的性能对比。
从表2可以看出,公开数据集组在经过图像增强以及二次迁移训练之后,无论是准确率还是F1值都有较大提升,这是因为公开数据集本身数据量较大,且其原始图像的质量较差,经过直方图均值化的对比度增强后,其训练出的模型准确度和F1值都可以得到提升。DW-CBMD组经过图像增强后,其准确率得到了一定程度的提升,但 F1 值未受到显著影响。而在 WL-CBMD 组经过图像增强后,无论是准确率还是 F1 值均有所提升。
通过对比二阶段迁移学习对模型训练的影响,发现二阶段迁移学习在 DW-CBMD组和 WL-CBMD组的准确率和 F1 值上都得到了提升,说明从公开数据集中学习到的特征通过2次迁移学习能够有效应用于中国人群的乳腺钼靶图像数据集。
在中国人乳腺钼靶图像的分类性能方面,当前国内外的研究通常使用公开数据集(如MIAS、CBIS-DDSM)对乳腺钼靶图像进行训练,并采用默认的窗口设置[11-12,14,19]。以RABIDAS等[11]、SHEN等[14]、董誉[19]的研究为例,均采用DDSM的默认窗口作为训练集,AUC值分别可以达到0.98、0.88以及0.99,REHMAN等[12]的研究没有使用AUC而是使用了准确率作为评价指标,其准确率可以达到0.93。然而,由于欧美女性的乳腺组织密度通常低于中国女性[1,18],肿块位置在默认窗口下更为清晰。因此,当本研究在复现董誉等[19]提出的乳腺钼靶肿块良恶性分类方法时发现,对以欧美女性为主的公开数据集进行默认窗口训练,模型的AUC值虽然可以达到0.98,但是,将相同方法应用于中国人群乳腺钼靶图像数据集CBMD时,AUC值仅为0.51(表1),提示中西方女性乳房在乳腺钼靶影像上具有一定差异。
针对中国人群的乳腺组织密度与欧美人群的差异特点,本研究提出了一种滑动窗口调整机制,该方法可以找到适合中国人群乳腺钼靶图像进行乳腺组织密度与肿块密度分离的最优窗宽窗位,以改善中国人群数据特征与欧美公开数据集特征之间的差异。实验结果显示,滑窗机制将AUC值从0.51显著提高到0.89(表1),显著提高了模型对中国人群乳腺钼靶图像CBMD的分类性能。并进一步通过二次迁移学习的方法,弥补中国人群数据集规模有限的问题,初步达到了对中国人群乳腺钼靶图像分类的需求。
在中国人群的代表性方面,本研究所使用的CBMD的数据主要来自中国西南地区。薛珂等[20] 研究表明,中国华北地区女性的乳房平均尺寸特征大于华南和西南地区,且随乳房尺寸增加,乳腺体积密度(volumetric breast density,VBD)呈下降趋势(VBD指乳腺中致密组织占总体积的比例)。这一结果说明华南和西南地区女性乳房的平均乳腺组织密度高于华北地区。因此,可以认为本研究选用的数据集在乳腺钼靶图像分类难度上高于华北地区,与国际公开数据集的差异更大,从而对中国人群的乳腺特征研究具有更强的针对性。当然,以此工作为基础,下一步仍需积极推动跨地区的多中心研究,联合更多医疗机构增强数据集多样性和区域代表性,进一步提升数据集的全面性和可靠性。
在数据增强方面,本研究通过拉伸、模糊、缩放、旋转和平移等5种变换进行数据扩充。虽然这些变换未引入新的医学特征,但本研究的模型通过2次迁移学习,从不同的数据集中学习到大量有用特征,在样本量有限的情况下理论上能有效提高模型的鲁棒性和泛化能力。并计划通过积极推进多中心研究,丰富数据集多样性,增加代表良性组织的数据,以获得更好的模型性能。
在临床验证与多中心研究方面,本研究主要基于公开数据集构建基础分类模型,并以中国人群数据集进行二阶段迁移学习。实验结果显著提升了中国人群乳腺钼靶图像的分类性能。下一步,计划利用目前自主研发的乳腺钼靶分类辅助系统进行临床推广试用,在补充临床验证的同时推动多中心研究,不断丰富数据集的多样性,提升模型的泛化能力,形成良性循环。同时,将参照本研究的思路,进一步探索肿块目标检测算法在中国人群中的适用性,不断完善和拓展针对中国人群的乳腺钼靶X线图像分类辅助系统的临床功能。
综上,研究结果证实,利用人工智能辅助诊断方法在中国人群中使用乳腺钼靶筛查具有潜力。基于此,本研究进一步研发了一款适用于中国人群的乳腺钼靶X线图像分类辅助系统。未来,研究团队将通过多中心推广应用与合作,力争在当前国内以超声筛查为主的背景下,推动乳腺钼靶筛查方法的普及,缩小与国际乳腺钼靶筛查规模之间的差距,以低成本的方式丰富乳腺癌筛查手段。
本研究通过引入滑动窗口调窗机制和二阶段迁移学习策略,成功将中国人群的乳腺钼靶图像分类的AUC值从文献复现模型的0.51提升至0.89,显著提升了乳腺钼靶图像分类模型在中国人群数据集上的性能,证实了中国人群的乳腺特征具备乳腺病变精确诊断的医学价值,为进一步完善中国人群乳腺钼靶图像数据库奠定了基础。在此基础上,本研究研发了一款适用于中国人群的乳腺钼靶分类辅助系统,期望通过临床试用和不断迭代完善,在促进更为便捷的乳腺癌早期筛查方法普及的同时,兼具培养年轻医生的教学作用,为广大患者带来更好的健康和生活质量。

参考文献 引证文献
排序方式:
1
高艳多,阎炯,赵胜,等. 1990—2019年中国女性乳腺癌发病和死亡趋势的年龄-时期-队列模型分析[J]. 中国预防医学杂志,2022,23(12):909-916.
GAO Y D,YAN J,ZHAO S,et al. Trends in incidence and mortality of female breast cancer in China from 1990 to 2019 using age-period-cohort analysis model[J]. Chin Prev Med,2022,23(12):909-916.
2
XU Y Y,GONG M Y,WANG Y,et al. Global trends and forecasts of breast cancer incidence and deaths[J]. Sci Data,2023,10(1):334.
3
郭亚梅,蒋凌燕,段正凡. 乳腺钼靶X线摄影诊断乳腺癌的应用价值分析[J]. 国际全科医学,2023.4(1):83-85.
GAO Y M,JIANG L Y,DUAN Z F,et al. The value of mammography in the diagnosis of breast cancer[J]. Int J Gen Med,2023.4(1):83-85.
4
LIAO J W,GUI Y,LI Z L,et al. Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population:a retrospective,multicentre,cohort study[J]. EClinicalMedicine,2023,60:102001.
5
FARAH L,DAVAZE-SCHNEIDER J,MARTIN T,et al. Are current clinical studies on artificial intelligence-based medical devices comprehensive enough to support a full health technology assessment:A systematic review[J]. Artif Intell Med,2023,140:102547.
6
MRAČKO A,VANOVČANOVÁ L,CIMRÁK I. Mammography datasets for neural networks-survey[J]. J Imaging,2023,9(5):95.
7
KIM C M,CHUNG K,PARK R C. Anomaly detection model of mammography using YOLOv4-based histogram[J]. Pers Ubiquitous Comput,2023,27(3):1233-1244.
8
LEE S E,HAN K,KIM E K. Application of artificial intelligence-based computer-assisted diagnosis on synthetic mammograms from breast tomosynthesis:comparison with digital mammograms[J]. Eur Radiol,2021,31(9):6929-6937.
9
WANG Y Q,TANG L,CHEN P P,et al. The role of a deep learning-based computer-aided diagnosis system and elastography in reducing unnecessary breast lesion biopsies[J]. Clin Breast Cancer,2023,23(3):e112-e121.
10
SIVIENGPHANOM S,GANDOMKAR Z,LEWIS S J,et al. Global radiomic features from mammography for predicting difficult-to-interpret normal cases[J]. J Digit Imag,2023,36(4):1541-1552.
11
RABIDAS R,MIDYA A,SADHU A,et al. Benign-malignant mass classification in mammogram using edge weighted local texture features[C]. Med Ima 2016:Comput Aided Diag-SPIE,2016,9785(1x):1-6.
12
REHMAN S U,KHAN M A,MASOOD A,et al. BRMI-net:deep learning features and flower pollination-controlled regula falsi-based feature selection framework for breast cancer recognition in mammography images[J]. Diagnostics,2023,13(9):1618.
13
LEE R S,GIMENEZ F,HOOGI A,et al. A curated mammography data set for use in computer-aided detection and diagnosis research[J]. Sci Data,2017,4:170177.
14
SHEN L,MARGOLIES L R,ROTHSTEIN J H,et al. Deep learning to improve breast cancer detection on screening mammography[J]. Sci Rep,2019,9:12495.
15
MOREIRA I C,AMARAL I,DOMINGUES I,et al. INbreast:toward a full-field digital mammographic database[J]. Acad Radiol,2012,19(2):236-248.
16
HEATH M,BOWYER K,KOPANS D,et al. Current status of the digital database for screening mammography[M]. Dordrecht:Springer Netherlands,1998:457-460.
17
SUCKLING J,PARKER J,ASTLEY S,et al. The Mammographic Image Analysis Society digital mammogram database[C]. Int Congr Ser,1994:375-378. https://www.repository.cam.ac.uk/handle/1810/250394.
18
彭芳芳,沈坤炜. 中西方女性乳腺密度与乳腺癌发病关系的研究进展[J]. 中国癌症防治杂志,2020,12(4):469-474.
PENG F F,SHEN K W. Research progress on the relationship between breast density and breast cancer in Chinese and western women[J]. Chin J Oncol Prev Treat,2020,12(4):469-474.
19
董誉. 乳腺钼靶图像中的肿块良恶性分类[D]. 武汉:华中科技大学,2020:8-36.
DONG Y. Classification of benign and malignant masses in mammography[D]. Wuhan:Huazhong University of Science and Technology,2020:8-36.
20
薛珂,徐辉,岳保荣,等. 我国女性乳腺体积密度及相关乳房特征定量研究[J]. 中华放射医学与防护杂志,2024,44(4):278-285.
XUE K,XU H,YUE B R,et al. Quantitative study on female breast bulk density and related breast characteristics in China[J]. Chin J Radiol Med Prot,2024,44(4):278-285.
2025年第47卷第1期
PDF下载
6
1
引用本文
BibTeX
文章信息
doi: 10.16016/j.2097-0927.202407001
  • 接收时间:2024-07-01
  • 首发时间:2026-10-30
  • 出版时间:2025-01-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-07-01
  • 修回日期:2024-10-30
基金
作者信息
    1陆军军医大学(第三军医大学)生物医学工程与影像医学系:医学图像学教研室,重庆
    2陆军军医大学(第三军医大学)生物医学工程与影像医学系:数字医学教研室,重庆
    3陆军特色医学中心(第三军医大学大坪医院)医学工程科,重庆

通讯作者:

乔梁,E-mail:
QIAO Liang,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ljjydxxb/CN/10.16016/j.2097-0927.202407001
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