Article(id=1190669165523513572, tenantId=1146029695717560320, journalId=1189873630562394117, issueId=1190669163988398295, articleNumber=null, orderNo=null, doi=10.11855/j.issn.0577-7402.0933.2025.0102, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1719331200000, receivedDateStr=2024-06-26, revisedDate=null, revisedDateStr=null, acceptedDate=1725811200000, acceptedDateStr=2024-09-09, onlineDate=1761807250624, onlineDateStr=2025-10-30, pubDate=1745769600000, pubDateStr=2025-04-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1761807250624, onlineIssueDateStr=2025-10-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1761807250624, creator=13701087609, updateTime=1761807250624, updator=13701087609, issue=Issue{id=1190669163988398295, tenantId=1146029695717560320, journalId=1189873630562394117, year='2025', volume='50', issue='4', pageStart='367', pageEnd='503', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1761807250258, creator=13701087609, updateTime=1761807667423, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1190670913772339410, tenantId=1146029695717560320, journalId=1189873630562394117, issueId=1190669163988398295, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1190670913772339411, tenantId=1146029695717560320, journalId=1189873630562394117, issueId=1190669163988398295, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=409, endPage=417, ext={EN=ArticleExt(id=1190669165716451558, articleId=1190669165523513572, tenantId=1146029695717560320, journalId=1189873630562394117, language=EN, title=The predictive value of high-kilovoltage CT radiomics for urate crystallization in gouty arthritis, columnId=1190310109000602400, journalTitle=Medical Journal of Chinese People’s Liberation Army, columnName=Clinical Research, runingTitle=null, highlight=null, articleAbstract=

Objective To explore the value of a combined model based on high-kilovoltage CT radiomics and clinical factors for predicting monosodium urate (MSU) crystal deposition in gouty arthritis. Methods The clinical data of 136 patients with MSU crystal deposition adjacent to joints confirmed by dual-energy CT (DECT) and 79 patients with non-MSU calcifications adjacent to joints were retrospectively analyzed. The dataset was randomly divided into a training set (n=150) and a validation set (n=65) at a ratio of 7:3 for the construction of predictive models. Radiomic features were extracted from high-kilovolt (135 kV) images, and 20 radiomic features were selected using minimum redundancy-maximum relevance and least absolute shrinkage and selection operator (LASSO) regression. Logistic regression, light gradient boosting machine (LightGBM), and support vector machine models were built based on the selected features, and the best-performing model was identified. Multivariate logistic regression analysis was used to screen for risk factors associated with MSU crystal deposition adjacent to joints. A nomogram model was then constructed by integrating radiomic features and clinical variables. The diagnostic performance of the models was evaluated by means of the receiver operating characteristics (ROC) area under the curve (AUC). Results Multivariate logistic regression analysis revealed that CT value was an independent risk factor for MSU crystal deposition adjacent to joints (P<0.001). Among the three machine-learning models, the LightGBM model demonstrated the best predictive performance and good dataset robustness. Therefore, the nomogram was constructed using the LightGBM model. The AUCs of the nomogram model for predicting MSU crystal deposition in the training and validation sets were 0.932 and 0.856, respectively, both exceeding 0.85 and significantly higher than those of the clinical model (De-long test, P<0.05). No statistically significant difference was observed between nomogram model and radiomics model (De-long test, P>0.05). Conclusions High-kilovoltage CT radiomics analysis can predict MSU crystal deposition adjacent to joints. The nomogram model and the radiomics model both demonstrate high diagnostic performance, which can provide valuable references for clinical decision-making.

, correspAuthors=Guo-Zheng Zhang, authorNote=null, correspAuthorsNote=
E-mail:
, copyrightStatement=null, copyrightOwner=null, 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, authorCompany=null, fund=null, authors=null, authorsList=Wei-Tao Huang, Guo-Zheng Zhang, Xiao-Wei Han), CN=ArticleExt(id=1190669409489400709, articleId=1190669165523513572, tenantId=1146029695717560320, journalId=1189873630562394117, language=CN, title=高千伏CT影像组学对痛风性关节炎单钠尿酸盐结晶的预测价值, columnId=1190310109164180259, journalTitle=解放军医学杂志, columnName=临床研究, runingTitle=null, highlight=null, articleAbstract=

目的 探讨基于高千伏CT影像组学和临床因素的联合模型预测痛风性关节炎单钠尿酸盐(MSU)结晶的价值。方法 回顾性分析2019年1月-2023年5月在衢州市人民医院经双能CT(DECT)明确诊断为关节旁MSU结晶沉积的136例患者和关节旁非MSU钙化的79例患者的临床资料;按7:3的比例随机分为训练集(n=150)和验证集(n=65)用于预测模型的构建及验证。从高千伏(135 kV)图像中提取影像组学特征,采用最小冗余-最大相关性和最小绝对收缩选择算子(LASSO)回归筛选出20个影像组学特征。采用逻辑回归、光梯度增强机(LightGBM)和支持向量机对所选特征进行建模,并选出性能最佳的模型。采用多因素logistic回归分析筛选关节旁MSU结晶沉积的危险因素,结合影像组学特征和临床变量构建列线图模型。采用受试者操作特征(ROC)曲线下面积(AUC)评价各模型的预测效能。结果 多因素logistic回归分析显示,CT值是关节旁MSU结晶沉积的独立危险因素(P<0.001)。在3种机器学习模型中,LightGBM模型具有最佳的预测性能和良好的数据集鲁棒性,因此采用LightGBM模型构建列线图。列线图模型在训练集和验证集中预测关节旁MSU结晶沉积的AUC分别为0.932和0.856,均高于0.85,明显高于临床模型(De-long检验,P<0.05),但与影像组学模型差异无统计学意义(De-long检验,P>0.05)。结论 基于高千伏CT影像组学分析可预测关节旁MSU结晶沉积,列线图模型及影像组学模型的预测效能均较高,可为临床决策提供参考。

, correspAuthors=张国正, authorNote=null, correspAuthorsNote=
张国正,E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=2syJWK40WzjOCz2+FJsvhA==, magXml=J36QIUaAF/ZJgFIRMt6ocg==, pdfUrl=null, pdf=gLlcydKYUQgaF/8a6Nv2Mg==, pdfFileSize=3806572, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=yxrpL4W4UBs7Mq37M7hvew==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=y6fYui8HJ228qEXbCCb5fw==, mapNumber=null, authorCompany=null, fund=null, authors=

黄渭涛,硕士研究生,主要从事人工智能及影像组学方面的研究

, authorsList=黄渭涛, 张国正, 韩小伟)}, authors=[Author(id=1190669409841722252, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, 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=1190669409904636814, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, authorId=1190669409841722252, language=EN, stringName=Wei-Tao Huang, firstName=Wei-Tao, middleName=null, lastName=Huang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Department of Radiology, Quzhou Hospital Affiliated to Wenzhou Medical University/Quzhou People's Hospital, Quzhou, Zhejiang 324000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1190669409967551375, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, authorId=1190669409841722252, language=CN, stringName=黄渭涛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=温州医科大学附属衢州医院/衢州市人民医院放射科,浙江衢州 324000, bio={"content":"

黄渭涛,硕士研究生,主要从事人工智能及影像组学方面的研究

"}, bioImg=null, bioContent=

黄渭涛,硕士研究生,主要从事人工智能及影像组学方面的研究

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1190669409736864648, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, xref=null, ext=[AuthorCompanyExt(id=1190669409745253257, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, companyId=1190669409736864648, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Department of Radiology, Quzhou Hospital Affiliated to Wenzhou Medical University/Quzhou People's Hospital, Quzhou, Zhejiang 324000, China), AuthorCompanyExt(id=1190669409753641866, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, companyId=1190669409736864648, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=温州医科大学附属衢州医院/衢州市人民医院放射科,浙江衢州 324000)])]), Author(id=1190669410026271633, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zgz_0007@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1190669410105963411, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, authorId=1190669410026271633, language=EN, stringName=Guo-Zheng Zhang, firstName=Guo-Zheng, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=Department of Radiology, Quzhou Hospital Affiliated to Wenzhou Medical University/Quzhou People's Hospital, Quzhou, Zhejiang 324000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1190669410198238100, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, authorId=1190669410026271633, language=CN, stringName=张国正, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=温州医科大学附属衢州医院/衢州市人民医院放射科,浙江衢州 324000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1190669409736864648, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, xref=null, ext=[AuthorCompanyExt(id=1190669409745253257, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, companyId=1190669409736864648, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Department of Radiology, Quzhou Hospital Affiliated to Wenzhou Medical University/Quzhou People's Hospital, Quzhou, Zhejiang 324000, China), AuthorCompanyExt(id=1190669409753641866, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, companyId=1190669409736864648, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=温州医科大学附属衢州医院/衢州市人民医院放射科,浙江衢州 324000)])]), Author(id=1190669410256958358, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, 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=1190669410328261528, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, authorId=1190669410256958358, language=EN, stringName=Xiao-Wei Han, firstName=Xiao-Wei, middleName=null, lastName=Han, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Department of Radiology, Quzhou Hospital Affiliated to Wenzhou Medical University/Quzhou People's Hospital, Quzhou, Zhejiang 324000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1190669410407953305, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, authorId=1190669410256958358, language=CN, stringName=韩小伟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=温州医科大学附属衢州医院/衢州市人民医院放射科,浙江衢州 324000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1190669409736864648, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, xref=null, ext=[AuthorCompanyExt(id=1190669409745253257, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, companyId=1190669409736864648, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Department of Radiology, Quzhou Hospital Affiliated to Wenzhou Medical University/Quzhou People's Hospital, Quzhou, Zhejiang 324000, China), AuthorCompanyExt(id=1190669409753641866, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, companyId=1190669409736864648, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=温州医科大学附属衢州医院/衢州市人民医院放射科,浙江衢州 324000)])])], keywords=[Keyword(id=1190669410496033690, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, orderNo=1, keyword=gouty arthritis), Keyword(id=1190669410567336859, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, orderNo=2, keyword=monosodium urate crystals), Keyword(id=1190669410663805852, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, orderNo=3, keyword=radiomics), Keyword(id=1190669410743497629, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, orderNo=4, keyword=dual energy CT), Keyword(id=1190669410877715358, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, orderNo=1, keyword=痛风性关节炎), Keyword(id=1190669410944824223, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, orderNo=2, keyword=单钠尿酸盐结晶), Keyword(id=1190669411007738784, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, orderNo=3, keyword=影像组学), Keyword(id=1190669411070653345, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, orderNo=4, keyword=双能CT)], refs=[Reference(id=1190669414094746557, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=1, pageStart=97, pageEnd=106, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=章晓云, 李华南, 李时斌, journalName=解放军医学杂志, refType=null, unstructuredReference=章晓云, 李华南, 李时斌, 等. 肠道菌群在痛风病变过程中的作用机制及治疗研究进展[J]. 解放军医学杂志, 2023, 48(1): 97-106., articleTitle=肠道菌群在痛风病变过程中的作用机制及治疗研究进展, refAbstract=null), Reference(id=1190669414153466814, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2020, volume=50, issue=3S, pageStart=S11, pageEnd=S16, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Singh JA, Gaffo A, journalName=Semin Arthritis Rheum, refType=null, unstructuredReference=Singh JA, Gaffo A. Gout epidemiology and comorbidities[J]. Semin Arthritis Rheum, 2020, 50(3S): S11-S16., articleTitle=Gout epidemiology and comorbidities, refAbstract=null), Reference(id=1190669414224769984, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2020, volume=16, issue=7, pageStart=380, pageEnd=390, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Dehlin M, Jacobsson L, Roddy E, journalName=Nat Rev Rheumatol, refType=null, unstructuredReference=Dehlin M, Jacobsson L, Roddy E. Global epidemiology of gout: prevalence, incidence, treatment patterns and risk factors[J]. Nat Rev Rheumatol, 2020, 16(7): 380-390., articleTitle=Global epidemiology of gout: prevalence, incidence, treatment patterns and risk factors, refAbstract=null), Reference(id=1190669414291878849, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2021, volume=191, issue=null, pageStart=33, pageEnd=38, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=Tang YM, Zhang L, Zhu SZ, journalName=Public Health, refType=null, unstructuredReference=Tang YM, Zhang L, Zhu SZ, et al. Gout in China, 1990-2017: the global burden of disease study 2017[J]. Public Health, 2021, 191: 33-38., articleTitle=Gout in China, 1990-2017: the global burden of disease study 2017, refAbstract=null), Reference(id=1190669414350599106, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2020, volume=19, issue=4, pageStart=293, pageEnd=303, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=中华医学会, journalName=中华全科医师杂志, refType=null, unstructuredReference=中华医学会. 痛风及高尿酸血症基层诊疗指南(2019)[J]. 中华全科医师杂志, 2020, 19(4): 293-303., articleTitle=痛风及高尿酸血症基层诊疗指南(2019), refAbstract=null), Reference(id=1190669414413513667, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2016, volume=34, issue=9, pageStart=1297, pageEnd=1302, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=Spek A, Strittmatter F, Graser A, journalName=World J Urol, refType=null, unstructuredReference=Spek A, Strittmatter F, Graser A, et al. Dual energy can accurately differentiate uric acid-containing urinary calculi from calcium stones[J]. World J Urol, 2016, 34(9): 1297-1302., articleTitle=Dual energy can accurately differentiate uric acid-containing urinary calculi from calcium stones, refAbstract=null), Reference(id=1190669414468039620, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2020, volume=30, issue=5, pageStart=2791, pageEnd=2801, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=McGrath TA, Frank RA, Schieda N, journalName=Eur Radiol, refType=null, unstructuredReference=McGrath TA, Frank RA, Schieda N, et al. Diagnostic accuracy of dual-energy computed tomography (DECT) to diferentiate uric acid from non-uric acid calculi: systematic review and meta-analysis[J]. Eur Radiol, 2020, 30(5): 2791-2801., articleTitle=Diagnostic accuracy of dual-energy computed tomography (DECT) to diferentiate uric acid from non-uric acid calculi: systematic review and meta-analysis, refAbstract=null), Reference(id=1190669414530954181, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2012, volume=48, issue=4, pageStart=441, pageEnd=446, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=Lambin P, Rios-Velazquez E, Leijenaar R, journalName=Eur J Cancer, refType=null, unstructuredReference=Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446., articleTitle=Radiomics: extracting more information from medical images using advanced feature analysis, refAbstract=null), Reference(id=1190669414644200390, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2019, volume=53, issue=6, pageStart=526, pageEnd=529, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=胡杉, 梁长虹, 刘再毅, journalName=中华放射学杂志, refType=null, unstructuredReference=胡杉, 梁长虹, 刘再毅, 等. 纹理分析及影像组学在非肿瘤病变的研究应用及进展[J]. 中华放射学杂志, 2019, 53(6): 526-529., articleTitle=纹理分析及影像组学在非肿瘤病变的研究应用及进展, refAbstract=null), Reference(id=1190669414723892167, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2024, volume=49, issue=7, pageStart=739, pageEnd=746, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=王月明, 喻航, 王淼煜, journalName=解放军医学杂志, refType=null, unstructuredReference=王月明, 喻航, 王淼煜, 等. CT影像组学特征在肺泡蛋白沉积症中的诊断价值[J]. 解放军医学杂志, 2024, 49(7): 739-746., articleTitle=CT影像组学特征在肺泡蛋白沉积症中的诊断价值, refAbstract=null), Reference(id=1190669414807778248, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2017, volume=51, issue=12, pageStart=979, pageEnd=982, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=陈瑾, 王海屹, 叶慧义, journalName=中华放射学杂志, refType=null, unstructuredReference=陈瑾, 王海屹, 叶慧义. 纹理分析在肿瘤影像学中的研究进展[J]. 中华放射学杂志, 2017, 51(12): 979-982., articleTitle=纹理分析在肿瘤影像学中的研究进展, refAbstract=null), Reference(id=1190669414879081417, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2021, volume=24, issue=33, pageStart=4196, pageEnd=4199, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=张妲, 黄志芳, 李新伦, journalName=中国全科医学, refType=null, unstructuredReference=张妲, 黄志芳, 李新伦, 等. 2015-2020年国内外痛风诊疗指南比较与解析[J]. 中国全科医学, 2021, 24(33) : 4196-4199., articleTitle=2015-2020年国内外痛风诊疗指南比较与解析, refAbstract=null), Reference(id=1190669414950384586, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2019, volume=18, issue=11, pageStart=1102, pageEnd=1105, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=刘巧楠, 丁韦仁, 刘林, journalName=中华全科医师杂志, refType=null, unstructuredReference=刘巧楠, 丁韦仁, 刘林, 等. 影像学检查方法在痛风性关节炎中的研究进展[J]. 中华全科医师杂志, 2019, 18(11): 1102-1105., articleTitle=影像学检查方法在痛风性关节炎中的研究进展, refAbstract=null), Reference(id=1190669415021687755, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2021, volume=94, issue=1121, pageStart=20200493, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=Xie Y, Li L, Luo R, journalName=Br J Radiol, refType=null, unstructuredReference=Xie Y, Li L, Luo R, et al. Diagnostic efficacy of joint ultrasonography, dual-energy computed tomography and minimally invasive arthroscopy on knee gouty arthritis, a comparative study[J]. Br J Radiol, 2021, 94(1121): 20200493., articleTitle=Diagnostic efficacy of joint ultrasonography, dual-energy computed tomography and minimally invasive arthroscopy on knee gouty arthritis, a comparative study, refAbstract=null), Reference(id=1190669415101379532, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2011, volume=31, issue=5, pageStart=1365, pageEnd=1375, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=Desai MA, Peterson JJ, Garner HW, journalName=RadioGraphics, refType=null, unstructuredReference=Desai MA, Peterson JJ, Garner HW, et al. Clinical utility of dual-energy CT for evaluation of tophaceous gout[J]. RadioGraphics, 2011, 31(5): 1365-1375., articleTitle=Clinical utility of dual-energy CT for evaluation of tophaceous gout, refAbstract=null), Reference(id=1190669415168488397, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2023, volume=62, issue=9, pageStart=1068, pageEnd=1076, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=徐东, 朱小霞, 邹和建, journalName=中华内科杂志, refType=null, unstructuredReference=徐东, 朱小霞, 邹和建, 等. 痛风诊疗规范[J]. 中华内科杂志, 2023, 62(9): 1068-1076., articleTitle=痛风诊疗规范, refAbstract=null), Reference(id=1190669415227208654, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2012, volume=71, issue=3, pageStart=470, pageEnd=472, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=Manger B, Lell M, Wacker J, journalName=Ann Rheum Dis, refType=null, unstructuredReference=Manger B, Lell M, Wacker J, et al. Detection of periarticular urate deposits with dual energy CT in patients with acute gouty arthritis[J]. Ann Rheum Dis, 2012, 71(3): 470-472., articleTitle=Detection of periarticular urate deposits with dual energy CT in patients with acute gouty arthritis, refAbstract=null), Reference(id=1190669415290123215, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2016, volume=17, issue=null, pageStart=91, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=Baer AN, Kurano T, Thakur UJ, journalName=BMC Musculoskelet Disord, refType=null, unstructuredReference=Baer AN, Kurano T, Thakur UJ, et al. Dual-energy computed tomography has limited sensitivity for non-tophaceous gout: a comparison study with tophaceous gout[J]. BMC Musculoskelet Disord, 2016, 17: 91., articleTitle=Dual-energy computed tomography has limited sensitivity for non-tophaceous gout: a comparison study with tophaceous gout, refAbstract=null), Reference(id=1190669415357232080, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2015, volume=74, issue=6, pageStart=1072, pageEnd=1077, url=null, language=null, rfNumber=[19], rfOrder=18, authorNames=Bongartz T, Glazebrook KN, Kavros SJ, journalName=Ann Rheum Dis, refType=null, unstructuredReference=Bongartz T, Glazebrook KN, Kavros SJ, et al. Dual-energy CT for the diagnosis of gout: an accuracy and diagnostic yield study[J]. Ann Rheum Dis, 2015, 74(6): 1072-1077., articleTitle=Dual-energy CT for the diagnosis of gout: an accuracy and diagnostic yield study, refAbstract=null), Reference(id=1190669415415952337, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2018, volume=199, issue=2, pageStart=487, pageEnd=494, url=null, language=null, rfNumber=[20], rfOrder=19, authorNames=Ganesan V, De S, Shkumat N, journalName=J Urol, refType=null, unstructuredReference=Ganesan V, De S, Shkumat N, et al. Accurately diagnosing uric acid stones from conventional computerized tomography imaging: development and preliminary assessment of a pixel mapping software[J]. J Urol, 2018, 199(2): 487-494., articleTitle=Accurately diagnosing uric acid stones from conventional computerized tomography imaging: development and preliminary assessment of a pixel mapping software, refAbstract=null), Reference(id=1190669415478866898, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2021, volume=12, issue=5, pageStart=50, pageEnd=54, url=null, language=null, rfNumber=[21], rfOrder=20, authorNames=刘欣, 杨海涛, 王琪琪, journalName=磁共振成像, refType=null, unstructuredReference=刘欣, 杨海涛, 王琪琪, 等. MR T2WI单序列纹理分析对类风湿性关节炎和痛风性关节炎的鉴别诊断价值[J]. 磁共振成像, 2021, 12(5): 50-54., articleTitle=MR T2WI单序列纹理分析对类风湿性关节炎和痛风性关节炎的鉴别诊断价值, refAbstract=null), Reference(id=1190669415537587155, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2020, volume=36, issue=1, pageStart=1, pageEnd=13, url=null, language=null, rfNumber=[22], rfOrder=21, authorNames=中华医学会内分泌学分会, journalName=中华内分泌代谢杂志, refType=null, unstructuredReference=中华医学会内分泌学分会. 中国高尿酸血症与痛风诊疗指南(2019)[J]. 中华内分泌代谢杂志, 2020, 36(1): 1-13., articleTitle=中国高尿酸血症与痛风诊疗指南(2019), refAbstract=null), Reference(id=1190669415600501716, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2002, volume=61, issue=1, pageStart=52, pageEnd=54, url=null, language=null, rfNumber=[23], rfOrder=22, authorNames=Gerster JC, Landry M, Dufresne L, journalName=Ann Rheum Dis, refType=null, unstructuredReference=Gerster JC, Landry M, Dufresne L, et al. Imaging of tophaceous gout: computed tomography provides specific images compared with magnetic resonance imaging and ultrasonography[J]. Ann Rheum Dis, 2002, 61(1): 52-54., articleTitle=Imaging of tophaceous gout: computed tomography provides specific images compared with magnetic resonance imaging and ultrasonography, refAbstract=null), Reference(id=1190669415655027669, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2015, volume=26, issue=7, pageStart=523, pageEnd=527, url=null, language=null, rfNumber=[24], rfOrder=23, authorNames=漆强, 邹玉林, 余晖, journalName=中国临床医学影像杂志, refType=null, unstructuredReference=漆强, 邹玉林, 余晖, 等. 痛风性关节炎的X线、CT和MRI诊断价值比较[J]. 中国临床医学影像杂志, 2015, 26(7): 523-527., articleTitle=痛风性关节炎的X线、CT和MRI诊断价值比较, refAbstract=null), Reference(id=1190669415709553622, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2023, volume=166, issue=null, pageStart=111018, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=24, authorNames=Nie P, Liu S, Zhou R, journalName=Eur J Radiol, refType=null, unstructuredReference=Nie P, Liu S, Zhou R, et al. A preoperative CT-based deep learning radiomics model in predicting the stage, size, grade and necrosis score and outcome in localized clear cell renal cell carcinoma: a multicenter study[J]. Eur J Radiol, 2023, 166: 111018., articleTitle=A preoperative CT-based deep learning radiomics model in predicting the stage, size, grade and necrosis score and outcome in localized clear cell renal cell carcinoma: a multicenter study, refAbstract=null), Reference(id=1190669415776662488, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2021, volume=100, issue=4, pageStart=870, pageEnd=880, url=null, language=null, rfNumber=[26], rfOrder=25, authorNames=Zheng J, Yu H, Batur J, journalName=Kidney Int, refType=null, unstructuredReference=Zheng J, Yu H, Batur J, et al. A multicenter study to develop a non-invasive radiomic model to identify urinary infection stone in vivo using machine-learning[J]. Kidney Int, 2021, 100(4): 870-880., articleTitle=A multicenter study to develop a non-invasive radiomic model to identify urinary infection stone in vivo using machine-learning, refAbstract=null), Reference(id=1190669415864742873, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=1, pageStart=37, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=26, authorNames=Wang Z, Yang G, Wang X, journalName=Urolithiasis, refType=null, unstructuredReference=Wang Z, Yang G, Wang X, et al. A combined model based on CT radiomics and clinical variables to predict uric acid calculi which have a good accuracy[J]. Urolithiasis, 2023, 51(1): 37., articleTitle=A combined model based on CT radiomics and clinical variables to predict uric acid calculi which have a good accuracy, refAbstract=null)], funds=[Fund(id=1190669413952140219, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, awardId=82171908, language=EN, fundingSource=National Natural Science Foundation of China(82171908), fundOrder=null, country=null), Fund(id=1190669414010860476, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, awardId=82171908, language=CN, fundingSource=国家自然科学基金(82171908), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1190669409736864648, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, xref=null, ext=[AuthorCompanyExt(id=1190669409745253257, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, companyId=1190669409736864648, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Department of Radiology, Quzhou Hospital Affiliated to Wenzhou Medical University/Quzhou People's Hospital, Quzhou, Zhejiang 324000, China), AuthorCompanyExt(id=1190669409753641866, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, companyId=1190669409736864648, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=温州医科大学附属衢州医院/衢州市人民医院放射科,浙江衢州 324000)])], figs=[ArticleFig(id=1190669411175510947, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Fig.1, caption=Flowchart of the process of inclusion and exclusion of participants in the study, figureFileSmall=zBO+n66DM6sofx/3uSMW6g==, figureFileBig=yxrpL4W4UBs7Mq37M7hvew==, tableContent=null), ArticleFig(id=1190669411267785636, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=图1, caption=研究对象纳入与排除的流程图

DECT. 双能CT; MSU. 单钠尿酸盐

, figureFileSmall=zBO+n66DM6sofx/3uSMW6g==, figureFileBig=yxrpL4W4UBs7Mq37M7hvew==, tableContent=null), ArticleFig(id=1190669411431363493, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Fig.2, caption=The flowchart of to build a combined model for predicting monosodium urate (MSU) crystal deposition in gouty arthritis, figureFileSmall=Aah+6dem9kkT1gUTe28SOw==, figureFileBig=tli5p+G0qiTyVr4HDm/NAA==, tableContent=null), ArticleFig(id=1190669411485889446, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=图2, caption=痛风性关节炎单钠尿酸盐(MSU)结晶联合预测模型的构建流程图

ROI. 感兴趣区;LASSO. 最小绝对收缩和选择算子;A. MSU结晶ROI的分割;B.从ROI和LASSO回归中提取影像组学特征用于特征分割;C. 构建影像组学列线图

, figureFileSmall=Aah+6dem9kkT1gUTe28SOw==, figureFileBig=tli5p+G0qiTyVr4HDm/NAA==, tableContent=null), ArticleFig(id=1190669411548804007, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Fig.3, caption=Imaging radiomics feature selection using the least absolute shrinkage and selection operator (LASSO) regression model, figureFileSmall=aXLhIyypovKeJlZXAC0ogw==, figureFileBig=+3quv+ANlqHl+fOnW1shQQ==, tableContent=null), ArticleFig(id=1190669411620107176, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=图3, caption=采用最小绝对收缩和选择算子(LASSO)回归模型进行影像组学特征选择

MSE. 均方误差;A. 使用LASSO回归模型进行影像组学特征选择,根据最小准则使用5折交叉验证确定最佳的参数λ(λ=0.0687),在最优λ=0.0687处绘制垂直虚线;B. 1843个影像组学特征的LASSO系数分布图,最终垂直线处20个影像学特征被保留

, figureFileSmall=aXLhIyypovKeJlZXAC0ogw==, figureFileBig=+3quv+ANlqHl+fOnW1shQQ==, tableContent=null), ArticleFig(id=1190669411678827433, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Fig.4, caption=The weight values of the 20 imaging radiomics features were calculated, figureFileSmall=fS00Bm7p+TOFEuJkNFJ3Xw==, figureFileBig=PNnJpreRP8EHqG8q+Fozuw==, tableContent=null), ArticleFig(id=1190669411737547690, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=图4, caption=20个影像组学特征的权重数值

LBP. 局部二值变换;M1、M2. 表示某种特定的模式或版本;GLSZM. 灰度级区域大小矩阵;GLCM. 灰度共生矩阵;GLRLM. 灰度级长跑矩阵;特征的系数越大提示其对结果影响越大

, figureFileSmall=fS00Bm7p+TOFEuJkNFJ3Xw==, figureFileBig=PNnJpreRP8EHqG8q+Fozuw==, tableContent=null), ArticleFig(id=1190669411813045163, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Fig.5, caption=The ROC curves of the three machine learning models in train set and validation set, figureFileSmall=fZRwQH2I7KNudQuzt9kYFA==, figureFileBig=bGXb/zEeMNz0yM+PklXAzw==, tableContent=null), ArticleFig(id=1190669411884348332, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=图5, caption=三种机器学习模型在训练集和验证集中的ROC曲线

逻辑回归(LR)、支持向量机(SVM)和光梯度增强机(LightGBM)机器学习模型在训练集(A)和验证集(B)中对应的ROC曲线,LightGBM模型在验证集中表现最好

, figureFileSmall=fZRwQH2I7KNudQuzt9kYFA==, figureFileBig=bGXb/zEeMNz0yM+PklXAzw==, tableContent=null), ArticleFig(id=1190669411947262893, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Fig.6, caption=Performance of the Nomogram model for prediction of monosodium urate (MSU) crystals, figureFileSmall=E+ASMOFtPF1Ln7PFbkdAuA==, figureFileBig=gR8thqysCGim5F2RAJyobw==, tableContent=null), ArticleFig(id=1190669411997594542, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=图6, caption=列线图模型预测MSU结晶沉积的效能

MSU. 单钠尿酸盐;A. 基于影像组学模型和有意义的临床因素构建的列线图模型;B. 临床模型、影像组学模型及列线图模型在训练集和验证集中的校准曲线,校准曲线表示拟合优度,45°虚线表示理想预测值,实线表示3种模型的预测效能。预测结果越接近理想预测线,模型的预测效果越好;C. 3种模型在训练集和验证集中的ROC曲线,列线图模型和影像组学模型的AUC值均>0.85,优于临床模型

, figureFileSmall=E+ASMOFtPF1Ln7PFbkdAuA==, figureFileBig=gR8thqysCGim5F2RAJyobw==, tableContent=null), ArticleFig(id=1190669412064703407, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Fig.7, caption=Decision curve analysis of the three models in the training set (A) and validation set (B), figureFileSmall=PEdYL1bVkNUhmncEMpntrA==, figureFileBig=XI+nqoCSGnJApMRIBg/ExA==, tableContent=null), ArticleFig(id=1190669412119229360, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=图7, caption=三种预测模型在训练集(A)及验证集(B)中的决策曲线分析

MSU. 单钠尿酸盐;Y轴是净收益,X轴表示阈值概率。蓝色、橙色和绿色线条分别表示临床模型、影像模型和列线图模型的净收益。与其他两种模型和简单诊断如所有患者均有MSU结晶(黑实线)或所有患者均无MSU结晶(黑虚线)相比,影像组学模型和列线图模型具有较高的净效益

, figureFileSmall=PEdYL1bVkNUhmncEMpntrA==, figureFileBig=XI+nqoCSGnJApMRIBg/ExA==, tableContent=null), ArticleFig(id=1190669412190532529, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Fig.8, caption=Nomogram score and the result of dual-energy CT (DECT) of one patient with gouty arthritis of the 1st interphalangeal joint of the left foot, figureFileSmall=iseSvaQldBflwTMKFFFtxQ==, figureFileBig=ZxuwWR7mvnHbZBTL85kXwQ==, tableContent=null), ArticleFig(id=1190669412278612914, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=图8, caption=1例左足第1趾间关节痛风性关节炎患者列线图评分与双能CT(DECT)检查结果

MSU. 单钠尿酸盐;A. 列线图评分为111分;B. 经DECT检查后重建处理显示左足第1趾间关节旁MSU结晶沉积,MSU结晶发生概率>0.75

, figureFileSmall=iseSvaQldBflwTMKFFFtxQ==, figureFileBig=ZxuwWR7mvnHbZBTL85kXwQ==, tableContent=null), ArticleFig(id=1190669412349916083, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Tab.1, caption=

Comparison of clinical data between two groups of patients

, figureFileSmall=null, figureFileBig=null, tableContent=
指标训练集(n=150)验证集(n=65)
MSU结晶(n=93)非MSU钙化(n=57)PMSU结晶(n=43)非MSU钙化(n=22)P
年龄(岁, x±s)58.4±17.457.3±16.10.62458.5±16.258.9±16.50.622
血清尿酸(μmol/L, x±s)612.29±559.16554.17±128.800.498520.88±147.31530.48±129.970.830
CT值(HU, x±s)362.43±182.49680.84±290.05<0.001358.49±202.93696.50±299.42<0.001
性别[例(%)]0.4440.731
89(95.7)52(91.2)43(100.0)21(95.5)
4(4.3)5(8.8)01(4.5)
关节面侵蚀[例(%)]63(67.7)34(59.6)0.40627(62.8)15(68.2)0.876
高血压[例(%)]25(26.9)40(70.2)1.00013(30.2)12(54.5)0.102
糖尿病[例(%)]14(15.1)23(40.4)<0.0018(18.6)6(27.3)0.627
肾结石[例(%)]25(26.9)28(49.1)0.01011(25.6)16(72.7)<0.001
饮酒史[例(%)]37(39.8)27(47.4)0.45812(27.9)16(72.7)0.284
), ArticleFig(id=1190669412417024948, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=表1, caption=

两组患者临床资料比较

, figureFileSmall=null, figureFileBig=null, tableContent=
指标训练集(n=150)验证集(n=65)
MSU结晶(n=93)非MSU钙化(n=57)PMSU结晶(n=43)非MSU钙化(n=22)P
年龄(岁, x±s)58.4±17.457.3±16.10.62458.5±16.258.9±16.50.622
血清尿酸(μmol/L, x±s)612.29±559.16554.17±128.800.498520.88±147.31530.48±129.970.830
CT值(HU, x±s)362.43±182.49680.84±290.05<0.001358.49±202.93696.50±299.42<0.001
性别[例(%)]0.4440.731
89(95.7)52(91.2)43(100.0)21(95.5)
4(4.3)5(8.8)01(4.5)
关节面侵蚀[例(%)]63(67.7)34(59.6)0.40627(62.8)15(68.2)0.876
高血压[例(%)]25(26.9)40(70.2)1.00013(30.2)12(54.5)0.102
糖尿病[例(%)]14(15.1)23(40.4)<0.0018(18.6)6(27.3)0.627
肾结石[例(%)]25(26.9)28(49.1)0.01011(25.6)16(72.7)<0.001
饮酒史[例(%)]37(39.8)27(47.4)0.45812(27.9)16(72.7)0.284
), ArticleFig(id=1190669413473989557, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Tab.2, caption=

Univariate and multivariate logistic regression analysis on risk factors of monosodium urate (MSU)

, figureFileSmall=null, figureFileBig=null, tableContent=
因素单因素logistic回归多因素logistic回归
OR(95%CI)POR(95%CI)P
肾结石0.795(0.695~0.909)0.0050.996(0.879~1.129)0.957
糖尿病0.726(0.626~0.84)0.0000.905(0.789~1.04)0.235
饮酒史0.93(0.814~1.062)0.365
高血压0.992(0.868~1.133)0.920
CT值0.999(0.999~0.999)0.0000.999(0.999~0.999)<0.001
血清尿酸1.000(1.000~1.000)0.442
年龄1.001(0.997~1.005)0.681
关节侵蚀1.087(0.947~1.247)0.317
性别1.205(0.914~1.59)0.266
), ArticleFig(id=1190669413557875638, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=表2, caption=

单钠尿酸盐(MSU)结晶沉积危险因素的单因素和多因素logistic回归分析

, figureFileSmall=null, figureFileBig=null, tableContent=
因素单因素logistic回归多因素logistic回归
OR(95%CI)POR(95%CI)P
肾结石0.795(0.695~0.909)0.0050.996(0.879~1.129)0.957
糖尿病0.726(0.626~0.84)0.0000.905(0.789~1.04)0.235
饮酒史0.93(0.814~1.062)0.365
高血压0.992(0.868~1.133)0.920
CT值0.999(0.999~0.999)0.0000.999(0.999~0.999)<0.001
血清尿酸1.000(1.000~1.000)0.442
年龄1.001(0.997~1.005)0.681
关节侵蚀1.087(0.947~1.247)0.317
性别1.205(0.914~1.59)0.266
), ArticleFig(id=1190669413633373111, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Tab.3, caption=

Predicting efficiency of the three models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型训练集(n=150)验证集(n=65)
AUC(95%CI)敏感度特异度准确度AUC(95%CI)敏感度特异度准确度
LR0.878(0.821~0.934)0.8570.7890.8140.863(0.750~0.977)0.7500.8890.837
LightGBM0.930(0.894~0.966)0.9680.7430.8260.866(0.751~0.981)0.7500.8890.837
SVM0.928(0.879~0.977)0.7940.9720.9070.898(0.795~1.000)0.7501.0000.907
), ArticleFig(id=1190669413696287672, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=表3, caption=

三种模型的预测效能

, figureFileSmall=null, figureFileBig=null, tableContent=
模型训练集(n=150)验证集(n=65)
AUC(95%CI)敏感度特异度准确度AUC(95%CI)敏感度特异度准确度
LR0.878(0.821~0.934)0.8570.7890.8140.863(0.750~0.977)0.7500.8890.837
LightGBM0.930(0.894~0.966)0.9680.7430.8260.866(0.751~0.981)0.7500.8890.837
SVM0.928(0.879~0.977)0.7940.9720.9070.898(0.795~1.000)0.7501.0000.907
), ArticleFig(id=1190669413767590841, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=EN, label=Tab.4, caption=

Diagnostic efficacy of monosodium urate (MSU) crystals of three models in the validation set and validation set

, figureFileSmall=null, figureFileBig=null, tableContent=
模型AUC(95%CI)准确度敏感度特异度
训练集
临床模型0.849(0.790~0.908)0.7910.7460.840
影像组学模型0.930(0.894~0.966)0.8260.9680.743
列线图模型0.932(0.898~0.966)0.8370.8730.817
验证集
临床模型0.803(0.646~0.961)0.8370.8120.885
影像组学模型0.866(0.751~0.981)0.8370.7500.889
列线图模型0.856(0.726~0.987)0.8370.8120.862
), ArticleFig(id=1190669413834699706, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1190669165523513572, language=CN, label=表4, caption=

三种模型在验证集和验证集中对MSU结晶沉积的预测效能

, figureFileSmall=null, figureFileBig=null, tableContent=
模型AUC(95%CI)准确度敏感度特异度
训练集
临床模型0.849(0.790~0.908)0.7910.7460.840
影像组学模型0.930(0.894~0.966)0.8260.9680.743
列线图模型0.932(0.898~0.966)0.8370.8730.817
验证集
临床模型0.803(0.646~0.961)0.8370.8120.885
影像组学模型0.866(0.751~0.981)0.8370.7500.889
列线图模型0.856(0.726~0.987)0.8370.8120.862
)], attaches=null, journal=Journal(id=1146441329971666965, delFlag=0, nameCn=解放军医学杂志, nameEn=Medical Journal of Chinese People’s Liberation Army, nameHistory1=null, nameHistory2=null, issn=0577-7402, eissn=null, cn=11-1056/R, coden=null, periodic=0, language=CN, oaType=是, ccby=CC BY-NC-ND, 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=6srot5PcoYX30Oa4xeTmeg==, journalPrice=null, startedYear=null, abbrevIsoEn=null, journalRemark=null, publicationField=null, createdTime=1751262512917, updatedTime=1761735725513, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=M, firstLetterEn=M, subjectCode=Life Sciences, subjectName=Life Sciences, subjectCodeEn=Life Sciences, subjectNameEn=null, picCn=6srot5PcoYX30Oa4xeTmeg==, picEn=ELwBh5xqrSTlIs7HmSNt2Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1190369167564968109, language=CN, name=解放军医学杂志, 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=1761735725537, updatedTime=1761735725537, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=#, submissionEditorUrl=#, submissionReviewUrl=#, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190369167615299758, language=EN, name=Medical Journal of Chinese People’s Liberation Army, 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=1761735725549, updatedTime=1761735725549, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=#, submissionEditorUrl=#, submissionReviewUrl=#, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1189873630562394117, websiteList=[Website(id=1189873845923287108, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189873630562394117, 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/jfjyxzz/CN, language=CN, createTime=1761617631655, createBy=18614031015, updateTime=1761622010471, updateBy=18614031015, name=解放军医学杂志-中文, tplId=1146099689490845704, title=解放军医学杂志, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189924939378520839, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=articleTextType, value=kx, createTime=1761629813284, updateTime=1761629813284, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939353355012, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=banner, value=null, createTime=1761629813278, updateTime=1761629813278, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939399492362, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=grayFlag, value=0, createTime=1761629813289, updateTime=1761629813289, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939344966403, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=logo, value=https://castjournals.cast.org.cn/joweb/jfjyxzz/CN/file/pic?fileId=+zXjYVhun8ZOAA6+aKx2hw==, createTime=1761629813276, updateTime=1761629813276, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939412075276, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=minRunFlag, value=0, createTime=1761629813292, updateTime=1761629813292, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939374326534, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jfjyxzz/CN/file/pic, createTime=1761629813283, updateTime=1761629813283, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939407880971, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=silenceFlag, value=0, createTime=1761629813291, updateTime=1761629813291, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939361743621, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1761629813280, updateTime=1761629813280, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939386909448, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=themeColor, value=null, createTime=1761629813286, updateTime=1761629813286, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939395298057, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=themeStyle, value=null, createTime=1761629813288, updateTime=1761629813288, creator=18614031015, updator=18614031015)]), Website(id=1189873846057504839, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189873630562394117, 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/jfjyxzz/EN, language=EN, createTime=1761617631687, createBy=18614031015, updateTime=1761622030030, updateBy=18614031015, name=解放军医学杂志-英文, tplId=1146101810881728533, title=Medical Journal of Chinese People’s Liberation Army, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189924968168223505, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=articleTextType, value=kx, createTime=1761629820148, updateTime=1761629820148, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968147251982, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=banner, value=null, createTime=1761629820143, updateTime=1761629820143, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968185000724, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=grayFlag, value=0, createTime=1761629820152, updateTime=1761629820152, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968138863373, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=logo, value=https://castjournals.cast.org.cn/joweb/jfjyxzz/EN/file/pic?fileId=+zXjYVhun8ZOAA6+aKx2hw==, createTime=1761629820141, updateTime=1761629820141, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968197583638, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=minRunFlag, value=0, createTime=1761629820155, updateTime=1761629820155, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968159834896, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jfjyxzz/EN/file/pic, createTime=1761629820146, updateTime=1761629820146, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968193389333, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=silenceFlag, value=0, createTime=1761629820154, updateTime=1761629820154, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968155640591, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1761629820145, updateTime=1761629820145, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968172417810, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=themeColor, value=null, createTime=1761629820149, updateTime=1761629820149, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968180806419, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=themeStyle, value=null, createTime=1761629820151, updateTime=1761629820151, creator=18614031015, updator=18614031015)])], journalTitle=解放军医学杂志, weixinUrl=null, journalUrl=http://zh.jfjyxzz.org.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Medical Journal of Chinese People’s Liberation Army, journalPhotoCn=6srot5PcoYX30Oa4xeTmeg==, journalPhotoEn=ELwBh5xqrSTlIs7HmSNt2Q==, journalFirstLetter=M, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/jfjyxzz/CN/10.11855/j.issn.0577-7402.0933.2025.0102, detailUrlEn=https://castjournals.cast.org.cn/joweb/jfjyxzz/EN/10.11855/j.issn.0577-7402.0933.2025.0102, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jfjyxzz/CN/PDF/10.11855/j.issn.0577-7402.0933.2025.0102, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jfjyxzz/EN/PDF/10.11855/j.issn.0577-7402.0933.2025.0102, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
高千伏CT影像组学对痛风性关节炎单钠尿酸盐结晶的预测价值
收藏切换
PDF下载
黄渭涛 , 张国正 * , 韩小伟
解放军医学杂志 | 临床研究 2025,50(4): 409-417
收起
收藏切换
解放军医学杂志 | 临床研究 2025, 50(4): 409-417
高千伏CT影像组学对痛风性关节炎单钠尿酸盐结晶的预测价值
全屏
黄渭涛, 张国正* , 韩小伟
作者信息
  • 温州医科大学附属衢州医院/衢州市人民医院放射科,浙江衢州 324000
  • 黄渭涛,硕士研究生,主要从事人工智能及影像组学方面的研究

通讯作者:

张国正,E-mail:
The predictive value of high-kilovoltage CT radiomics for urate crystallization in gouty arthritis
Wei-Tao Huang, Guo-Zheng Zhang* , Xiao-Wei Han
Affiliations
  • Department of Radiology, Quzhou Hospital Affiliated to Wenzhou Medical University/Quzhou People's Hospital, Quzhou, Zhejiang 324000, China
出版时间: 2025-04-28 doi: 10.11855/j.issn.0577-7402.0933.2025.0102
文章导航
收藏切换

目的 探讨基于高千伏CT影像组学和临床因素的联合模型预测痛风性关节炎单钠尿酸盐(MSU)结晶的价值。方法 回顾性分析2019年1月-2023年5月在衢州市人民医院经双能CT(DECT)明确诊断为关节旁MSU结晶沉积的136例患者和关节旁非MSU钙化的79例患者的临床资料;按7:3的比例随机分为训练集(n=150)和验证集(n=65)用于预测模型的构建及验证。从高千伏(135 kV)图像中提取影像组学特征,采用最小冗余-最大相关性和最小绝对收缩选择算子(LASSO)回归筛选出20个影像组学特征。采用逻辑回归、光梯度增强机(LightGBM)和支持向量机对所选特征进行建模,并选出性能最佳的模型。采用多因素logistic回归分析筛选关节旁MSU结晶沉积的危险因素,结合影像组学特征和临床变量构建列线图模型。采用受试者操作特征(ROC)曲线下面积(AUC)评价各模型的预测效能。结果 多因素logistic回归分析显示,CT值是关节旁MSU结晶沉积的独立危险因素(P<0.001)。在3种机器学习模型中,LightGBM模型具有最佳的预测性能和良好的数据集鲁棒性,因此采用LightGBM模型构建列线图。列线图模型在训练集和验证集中预测关节旁MSU结晶沉积的AUC分别为0.932和0.856,均高于0.85,明显高于临床模型(De-long检验,P<0.05),但与影像组学模型差异无统计学意义(De-long检验,P>0.05)。结论 基于高千伏CT影像组学分析可预测关节旁MSU结晶沉积,列线图模型及影像组学模型的预测效能均较高,可为临床决策提供参考。

痛风性关节炎  /  单钠尿酸盐结晶  /  影像组学  /  双能CT

Objective To explore the value of a combined model based on high-kilovoltage CT radiomics and clinical factors for predicting monosodium urate (MSU) crystal deposition in gouty arthritis. Methods The clinical data of 136 patients with MSU crystal deposition adjacent to joints confirmed by dual-energy CT (DECT) and 79 patients with non-MSU calcifications adjacent to joints were retrospectively analyzed. The dataset was randomly divided into a training set (n=150) and a validation set (n=65) at a ratio of 7:3 for the construction of predictive models. Radiomic features were extracted from high-kilovolt (135 kV) images, and 20 radiomic features were selected using minimum redundancy-maximum relevance and least absolute shrinkage and selection operator (LASSO) regression. Logistic regression, light gradient boosting machine (LightGBM), and support vector machine models were built based on the selected features, and the best-performing model was identified. Multivariate logistic regression analysis was used to screen for risk factors associated with MSU crystal deposition adjacent to joints. A nomogram model was then constructed by integrating radiomic features and clinical variables. The diagnostic performance of the models was evaluated by means of the receiver operating characteristics (ROC) area under the curve (AUC). Results Multivariate logistic regression analysis revealed that CT value was an independent risk factor for MSU crystal deposition adjacent to joints (P<0.001). Among the three machine-learning models, the LightGBM model demonstrated the best predictive performance and good dataset robustness. Therefore, the nomogram was constructed using the LightGBM model. The AUCs of the nomogram model for predicting MSU crystal deposition in the training and validation sets were 0.932 and 0.856, respectively, both exceeding 0.85 and significantly higher than those of the clinical model (De-long test, P<0.05). No statistically significant difference was observed between nomogram model and radiomics model (De-long test, P>0.05). Conclusions High-kilovoltage CT radiomics analysis can predict MSU crystal deposition adjacent to joints. The nomogram model and the radiomics model both demonstrate high diagnostic performance, which can provide valuable references for clinical decision-making.

gouty arthritis  /  monosodium urate crystals  /  radiomics  /  dual energy CT
黄渭涛, 张国正, 韩小伟. 高千伏CT影像组学对痛风性关节炎单钠尿酸盐结晶的预测价值. 解放军医学杂志, 2025 , 50 (4) : 409 -417 . DOI: 10.11855/j.issn.0577-7402.0933.2025.0102
Wei-Tao Huang, Guo-Zheng Zhang, Xiao-Wei Han. The predictive value of high-kilovoltage CT radiomics for urate crystallization in gouty arthritis[J]. Medical Journal of Chinese People’s Liberation Army, 2025 , 50 (4) : 409 -417 . DOI: 10.11855/j.issn.0577-7402.0933.2025.0102
痛风性关节炎(gouty arthritis,GA)是一种代谢性、晶体相关性关节风湿性疾病,其诱因为嘌呤代谢紊乱和(或)尿酸排泄减少引起的高尿酸血症所致的单钠尿酸盐(monosodium urate,MSU)结晶在关节周围蓄积[1],好发于第一跖趾关节。随着高蛋白、高嘌呤饮食的增多,GA已成为国内临床的多发病、常见病[2]。近年来的统计数据显示,GA患病率在欧美发达国家为3%~5%[3],在中国为1%~3%[4-5],并呈年轻化趋势。目前诊断GA的金标准为关节腔穿刺或痛风石抽吸物MSU结晶检查,因其为有创操作,应用范围受限;双能CT(dual energy CT,DECT)可用于识别关节MSU结晶沉积,但设备昂贵,在基层及偏远地区医院难以普及,且增加了患者的照射剂量和治疗费用[6-7]。影像组学可通过病灶分割、特征数据提取、数据库建立和个体化数据分析等步骤,解码隐含在医学影像中的数字化信息,用于疾病的诊治和预后评估[8]。本研究采用CT影像组学方法,基于DECT的高千伏(135 kV)单序列图像联合部分临床指标建立列线图模型,用于识别和预测关节旁MSU结晶沉积,旨在为GA病程进展和药物治疗效果的评估提供参考依据。
选取2019年1月-2023年5月在衢州市人民医院行DECT关节平扫的215例患者的临床及影像资料进行回顾性分析;其中经DECT检查诊断为MSU结晶者136例,诊断为非MSU钙化者79例;按7:3的比例随机分为训练集(n=150,其中MSU结晶者93例,非MSU钙化者57例)与验证集(n=65,其中MSU结晶者43例,非MSU钙化者22例),分别用于预测模型的构建及验证。纳入标准:(1)完成DECT扫描及能谱分析;(2)影像资料完整;(3)临床资料完整。排除标准:(1)MSU结晶太小,无法进行勾画;(2)CT图像质量不高;(3)结晶成分未明确。临床基线资料包括年龄、性别、血液分析、饮酒史及相关慢性病史结果,均来自医院病历管理系统。本研究经衢州市人民医院伦理委员会审批(2024-059),免除患者知情同意要求。病例筛选过程如图1所示。
CT图像采用东芝Aquilion one TSX-301C 320排双能CT扫描仪采集,管电压为135 kV和80 kV,管电流自动控制采用CareDoes4D,重建层厚0.5 mm,层间距0.5 mm,球管旋转时间0.275 s。将所有CT图像传送到工作站进行审查和分析。CT的DICOM图像来自图片归档和通信系统(PACS),图像预处理为窗位400 HU,窗宽1600 HU。使用开源软件ITK-SNAP(版本3.4)绘制ROI。由两名放射科医师逐层沿病灶边缘勾画ROI。为保证数据的可靠性,在勾画ROI时尽量放大图像,避免重叠邻近的钙化及关节骨质。
采用PyRadiomics平台(版本3.0)提取影像组学特征。为了保证特征的鲁棒性,对所有患者的每个特征值进行灰度离散化、重采样和Z-score归一化处理。影像组学特征包括一阶、二阶、高阶影像组学特征[灰度共现矩阵(GLCM)、灰度大小区域矩阵(GLSZM)、灰度游程矩阵(GLRLM)、邻域灰度色调差矩阵(NGTDM)、相邻灰度依赖矩阵(GLDM)、高斯拉普拉斯算子,以及具有高通(H)或低通(L)滤波器的所有可能组合的小波]。首先,使用观察者内和观察者间的组内相关系数(intraclass correlation coefficients,ICC)保证特征的一致性和重现性,并将ICC>0.80的特征纳入后续分析。对于重复性高的特征,计算Spearman等级相关系数来表示特征之间的关系,并保留相关系数>0.9的任意一对特征中的一个。然后,使用最小绝对收缩和选择算子(LASSO)回归模型对组学特征进行降维并构建影像组学标签。基于正则化权重λ,LASSO将所有回归系数压缩为0,并将无关特征的系数精确设置为0。为了确定最优的λ,使用10次最小标准的交叉验证,其中交叉验证误差最小处的λ值为最优值。其余具有非零系数的特征用于回归模型拟合,并组合形成影像组学标签。影像组学分析过程涉及的关键步骤包括CT图像采集、病灶分割、特征提取和选择及模型构建(图2)。
采用单因素和多因素logistic回归分析MSU结晶沉积的危险因素。使用LASSO特征选择后,采用3种不同的机器学习分类器进行监督学习,包括逻辑回归(logistic regression,LR)、光梯度增强机(light gradient boosting machine,LightGBM)和支持向量机(support vector machine,SVM)。采用5折交叉验证的方法获得最终的影像组学标签并确定最佳分类器。计算各预测模型预测关节旁MSU结晶沉积的受试者操作特征(receiver operating characteristic,ROC)曲线下面积(AUC)、准确度(ACC)、敏感度(SEN)和特异度(SPE),评估其预测效能。AUC最大的模型被认为最优。
采用R软件(v4.0.2)进行统计分析。计量数据符合正态分布时以x±s表示,组间比较采用独立样本t检验,不符合正态分布时以M(Q1Q3)表示,组间比较采用Mann-Whitney U检验。计数资料以例(%)表示,组间比较采用χ2检验或Fisher确切概率法。所有机器学习模型的性能指标,包括AUC、ACC、SEN、SPE、阳性预测值(PPV)、阴性预测值(NPV)和F1评分,均与金标准进行一致性评估。采用De-long检验比较AUC值,Hosmer-Lemeshow检验评估预测模型的预测概率和实际发生概率。P<0.05为差异有统计学意义。
纳入患者的临床资料见表1。训练集中,两组CT值、糖尿病、肾结石、饮酒史差异有统计学意义(P<0.05);验证集中,两组CT值、肾结石差异有统计学意义(P<0.05)。多因素logistic回归分析显示,仅CT值为关节旁MSU结晶沉积的独立危险因素(P<0.001,表2)。当患者伴有临床症状(如红肿、疼痛等)的关节经DECT扫描显示病患关节旁高密度钙化灶CT值较低(OR=0.999,95%CI 0.999~0.999)时,则有较大概率为MSU结晶沉积。
从患者的CT图像中共提取出1834个影像组学特征;经过5折交叉验证的方差分析和LASSO筛选(图3A、B),最终保留20个特征(图4)。将所有患者资料按照7:3的比例随机分为训练集(n=150)与验证集(n=65),然后采用3种机器学习方法建立影像组学模型(图5A、B),模型的预测效能如表3所示。其中LightGBM模型在训练集中的预测效能高于LR和SVM模型,在训练集和验证集中的性能相似,且性能稳定。因此,采用LightGBM模型构建列线图模型。采用logistic回归根据所选特征参数建立预测模型,并计算每个样本的影像组学标签(Rad-signature)以反映MSU结晶沉积的风险。Rad-signature为构建模型时影像组学特征与相应系数之和,各特征对应的系数见图4
纳入病灶CT值、Rad-signature构建列线图模型,如图6A所示。校准曲线与Hosmer-Lemeshow检验显示列线图模型具有良好的校准度和拟合优度(图6B)。临床模型、影像组学模型和列线图模型在训练集和验证集中的预测效能见表4。各模型的ROC曲线如图6C所示。De-long检验显示,在训练集中,列线图模型的预测效能与影像组学模型比较差异无统计学意义(P=0.511),但列线图模型的预测效能优于临床模型(P=0.016);在验证集中,影像组学模型和列线图模型的预测效能均优于临床模型(P<0.05),前两者之间比较差异无统计学意义(P=0.301)。决策曲线分析显示,影像组学模型和列线图模型在训练集和验证集中识别MSU结晶的总净效益均高于临床模型(图7)。
图8A显示了列线图的典型临床应用模式。一位57岁男性患者因左足第1趾间关节红肿、疼痛及足活动受限入院。DECT显示左足第1趾间关节旁钙化灶CT均值为550 HU,影像组学标签为0.85,病灶列线图评分为111分,关节旁MSU结晶沉积概率>0.75。DECT检查后重建图亦显示病灶为MSU结晶(图8B)。
2012年Lambin等[8]提出了影像组学的概念。作为一种新兴的诊断方法,影像组学凭借对海量影像数据信息更深层次的挖掘,可解析影像与基因和临床信息(分型、疗效和预后等)的关联,促进个性化、精准化的治疗[9-10]。近年来,影像组学方法已成功应用于前列腺癌、肾癌、膀胱癌等泌尿系统疾病的术前诊断、成分识别及预后预测[11];但关于非肿瘤性疾病的影像组学文献较少,其中关于GA预测识别的应用研究更为少见。
高尿酸血症是GA发病的主要危险因素。当血清尿酸盐>6.8 mg/dl时可导致MSU结晶沉积,但血清尿酸水平升高不一定会导致MSU结晶沉积,且血尿酸水平正常的患者亦可发病。此外,部分GA患者无临床症状或仅有轻微不适,即无症状高尿酸血症或无症状MSU晶体沉积期[12-13]。因此,仅依据血尿酸增高诊断GA时误诊率较高,因而需结合其他影像学检查或穿刺活检进行综合诊断。目前GA诊断的金标准为关节腔穿刺或痛风石抽吸物MSU结晶检查,活检发现偏振光显微镜下表现为2~20 μm负性双折光的针状或杆状MSU晶体[14];但即使是痛风急性发作时该检查亦可呈阴性,加之其为有创操作,患者适应性较低,且如患者无症状或临床表现不典型、血尿酸水平正常或因禁忌证无法进行穿刺活检操作时,会显著增加GA的诊断难度[15]。以往GA相关无创诊断研究多集中于DECT对痛风石检出的相关应用。另外,根据2015年美国风湿病学会(ACR)和欧洲抗风湿病联盟(EULAR)共同制订的痛风分类标准,当得分≥8分时可确诊痛风,其中影像学检查部分提出,当DECT显示MSU结晶沉积可得4分,其诊断痛风的敏感度和特异度均较高[16]。但在GA疾病早期、尿酸水平升高不显著、痛风石较小/密度较低或未出现痛风石的痛风患者中,DECT的敏感性偏低、阴性率较高,同时亦有假阳性的情况[17-19]。影像组学通过高效、大量提取影像特征,更加客观和定量地描述病变特征,可提供一种相对无创的预测识别方式。目前影像组学应用于GA的研究较少见。Ganesan等[20]在比较尿酸结石和钙化结石时发现,不同成分结石的核心和外围衰减有差异;根据这一特点,他们绘制了结石衰减的二维分布情况,并构建了一个半自动算法来处理图像,结果显示其敏感度为89%,特异度为91%,效果良好。刘欣等[21]回顾性分析经临床确诊的类风湿关节炎(RA)患者(81个关节)和GA患者(61个关节)的MRI图像,从T2WI脂肪抑制单序列图像中提取纹理特征进行进一步学习分析,发现影像组学及纹理分析能有效鉴别RA与GA,且不同特征集纹理分析对于鉴别RA与GA均具有一定价值,其中以一阶统计量特征最佳。本研究利用CT图像采用不同机器学习方法预测GA患者的MSU结晶沉积。
本组患者以男性为主,男女比例约20.5:1,高于以往痛风的流行病学研究[22],可能与部分高尿酸血症患者无MSU结晶析出有关。本研究的临床模型中,只有CT值(P<0.001)是有价值的独立危险因素。Gerster等[23]测出痛风石的CT值为(189.9±6.2) HU,漆强等[24]测得痛风石的CT值为70~250 HU,密度高于软组织,但低于骨骼,提示CT能通过测定组织的CT值更好地显示痛风结晶。本研究显示,LR、LightGBM和SVM 3种机器算法在训练集中预测MSU结晶沉积的AUC分别为0.878、0.930、0.928,在验证集中的AUC分别为0.863、0.866、0.898,3种机器算法效能均较好(AUC>0.850),其中以LightGBM最佳,在训练集中的AUC、敏感度及特异度分别为0.930、0.968和0.743。LightGBM是一种高效、准确且易于使用的机器学习算法,相比LR、SVM等其他学习算法及传统的梯度提升树,具有更快的训练速度,同时可保持模型的准确性。本研究中选择的大多数特征为高阶滤波和小波纹理特征,这些特征虽然难以解读,但能更详细地反映病灶的异质性和组织学状态[25]。Zheng等[26]从3个中心1198例符合条件的尿石症患者CT图像中提取影像组学特征,研究尿中产生脲酶细菌的存在与否与尿pH值的关系并构建列线图模型,该模型在训练集和3个外部验证集的AUC分别为0.898、0.832、0.825、0.812。Wang等[27]报道,基于常规CT的影像组学模型对尿酸性结石和非尿酸性结石的鉴别效果较好,其中结合影像组学特征和临床变量构建的联合模型具有更好的性能和良好的数据鲁棒性,模型在训练集中的AUC达0.878,在验证集中的AUC达0.867;该模型可帮助外科医师制订适宜的治疗和预防方案。本研究构建的模型与上述报道相近,将影像组学模型与临床特征相结合构建列线图模型,其在训练集中预测MSU结晶的AUC达0.932,在验证集中的AUC达0.856,与上述两项研究结果相近。但与上述两项研究结果不同的是,本研究构建的列线图模型与影像组学模型之间差异无统计学意义,可能与纳入列线图模型的临床因素较少有关,有待后续进一步分析及优化。
本研究存在一定局限性。首先,本研究为单中心研究,由于不同医院医疗设备和扫描参数的差异,本研究建立的人工智能模型扩大应用的有效性有待来自不同中心更大样本集的验证;其次,本研究为回顾性研究,采用的图像为DECT中高千伏(135 kV)图像,具有一定的局限性,未来可采用常规CT图像开展前瞻性研究,使其有更广泛的适用性及普及性。随着人工智能的不断进步及相应技术难题和限制的逐步解决,其在临床上的应用前景将越来越广阔。
  • 国家自然科学基金(82171908)
参考文献 引证文献
排序方式:
[1]
章晓云, 李华南, 李时斌, 等. 肠道菌群在痛风病变过程中的作用机制及治疗研究进展[J]. 解放军医学杂志, 2023, 48(1): 97-106.
[2]
Singh JA, Gaffo A. Gout epidemiology and comorbidities[J]. Semin Arthritis Rheum, 2020, 50(3S): S11-S16.
[3]
Dehlin M, Jacobsson L, Roddy E. Global epidemiology of gout: prevalence, incidence, treatment patterns and risk factors[J]. Nat Rev Rheumatol, 2020, 16(7): 380-390.
[4]
Tang YM, Zhang L, Zhu SZ, et al. Gout in China, 1990-2017: the global burden of disease study 2017[J]. Public Health, 2021, 191: 33-38.
[5]
中华医学会. 痛风及高尿酸血症基层诊疗指南(2019)[J]. 中华全科医师杂志, 2020, 19(4): 293-303.
[6]
Spek A, Strittmatter F, Graser A, et al. Dual energy can accurately differentiate uric acid-containing urinary calculi from calcium stones[J]. World J Urol, 2016, 34(9): 1297-1302.
[7]
McGrath TA, Frank RA, Schieda N, et al. Diagnostic accuracy of dual-energy computed tomography (DECT) to diferentiate uric acid from non-uric acid calculi: systematic review and meta-analysis[J]. Eur Radiol, 2020, 30(5): 2791-2801.
[8]
Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446.
[9]
胡杉, 梁长虹, 刘再毅, 等. 纹理分析及影像组学在非肿瘤病变的研究应用及进展[J]. 中华放射学杂志, 2019, 53(6): 526-529.
[10]
王月明, 喻航, 王淼煜, 等. CT影像组学特征在肺泡蛋白沉积症中的诊断价值[J]. 解放军医学杂志, 2024, 49(7): 739-746.
[11]
陈瑾, 王海屹, 叶慧义. 纹理分析在肿瘤影像学中的研究进展[J]. 中华放射学杂志, 2017, 51(12): 979-982.
[12]
张妲, 黄志芳, 李新伦, 等. 2015-2020年国内外痛风诊疗指南比较与解析[J]. 中国全科医学, 2021, 24(33) : 4196-4199.
[13]
刘巧楠, 丁韦仁, 刘林, 等. 影像学检查方法在痛风性关节炎中的研究进展[J]. 中华全科医师杂志, 2019, 18(11): 1102-1105.
[14]
Xie Y, Li L, Luo R, et al. Diagnostic efficacy of joint ultrasonography, dual-energy computed tomography and minimally invasive arthroscopy on knee gouty arthritis, a comparative study[J]. Br J Radiol, 2021, 94(1121): 20200493.
[15]
Desai MA, Peterson JJ, Garner HW, et al. Clinical utility of dual-energy CT for evaluation of tophaceous gout[J]. RadioGraphics, 2011, 31(5): 1365-1375.
[16]
徐东, 朱小霞, 邹和建, 等. 痛风诊疗规范[J]. 中华内科杂志, 2023, 62(9): 1068-1076.
[17]
Manger B, Lell M, Wacker J, et al. Detection of periarticular urate deposits with dual energy CT in patients with acute gouty arthritis[J]. Ann Rheum Dis, 2012, 71(3): 470-472.
[18]
Baer AN, Kurano T, Thakur UJ, et al. Dual-energy computed tomography has limited sensitivity for non-tophaceous gout: a comparison study with tophaceous gout[J]. BMC Musculoskelet Disord, 2016, 17: 91.
[19]
Bongartz T, Glazebrook KN, Kavros SJ, et al. Dual-energy CT for the diagnosis of gout: an accuracy and diagnostic yield study[J]. Ann Rheum Dis, 2015, 74(6): 1072-1077.
[20]
Ganesan V, De S, Shkumat N, et al. Accurately diagnosing uric acid stones from conventional computerized tomography imaging: development and preliminary assessment of a pixel mapping software[J]. J Urol, 2018, 199(2): 487-494.
[21]
刘欣, 杨海涛, 王琪琪, 等. MR T2WI单序列纹理分析对类风湿性关节炎和痛风性关节炎的鉴别诊断价值[J]. 磁共振成像, 2021, 12(5): 50-54.
[22]
中华医学会内分泌学分会. 中国高尿酸血症与痛风诊疗指南(2019)[J]. 中华内分泌代谢杂志, 2020, 36(1): 1-13.
[23]
Gerster JC, Landry M, Dufresne L, et al. Imaging of tophaceous gout: computed tomography provides specific images compared with magnetic resonance imaging and ultrasonography[J]. Ann Rheum Dis, 2002, 61(1): 52-54.
[24]
漆强, 邹玉林, 余晖, 等. 痛风性关节炎的X线、CT和MRI诊断价值比较[J]. 中国临床医学影像杂志, 2015, 26(7): 523-527.
[25]
Nie P, Liu S, Zhou R, et al. A preoperative CT-based deep learning radiomics model in predicting the stage, size, grade and necrosis score and outcome in localized clear cell renal cell carcinoma: a multicenter study[J]. Eur J Radiol, 2023, 166: 111018.
[26]
Zheng J, Yu H, Batur J, et al. A multicenter study to develop a non-invasive radiomic model to identify urinary infection stone in vivo using machine-learning[J]. Kidney Int, 2021, 100(4): 870-880.
[27]
Wang Z, Yang G, Wang X, et al. A combined model based on CT radiomics and clinical variables to predict uric acid calculi which have a good accuracy[J]. Urolithiasis, 2023, 51(1): 37.
2025年第50卷第4期
PDF下载
664
309
引用本文
BibTeX
文章信息
doi: 10.11855/j.issn.0577-7402.0933.2025.0102
  • 接收时间:2024-06-26
  • 首发时间:2025-10-30
  • 出版时间:2025-04-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-06-26
  • 录用日期:2024-09-09
基金
National Natural Science Foundation of China(82171908)
国家自然科学基金(82171908)
作者信息
    温州医科大学附属衢州医院/衢州市人民医院放射科,浙江衢州 324000

通讯作者:

张国正,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jfjyxzz/CN/10.11855/j.issn.0577-7402.0933.2025.0102
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

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

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