前列腺癌瘤内及瘤周MRI影像组学对骨转移的诊断价值
R737.25; 目的 探讨基于磁共振成像(MRI)的前列腺癌(PCa)瘤内及瘤周影像组学对骨转移的诊断价值.方法 收集2018年1月-2023年1月在甘肃省人民医院经组织穿刺病理学检查确诊为PCa的211例患者的临床资料进行回顾性分析.将患者按照7:3的比例随机分为训练集(n=147)与验证集(n=64);分别从患者的T2加权成像(T2WI)、扩散加权成像(DWI)及扩散系数成像(ADC)3个序列勾画感兴趣区(ROIs),用于提取影像组学特征;使用Z-score(正则化)、LASSO算法进行影像组学特征的降维、选择、构建;然后基于逻辑回归(LR)机器学习分类器构建模型;绘制受试者操作特征(R...
Saved in:
| Published in | 解放军医学杂志 Vol. 50; no. 1; pp. 1 - 8 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
甘肃中医药大学第一临床医学院,甘肃 兰州 730000%兰州大学第一临床医学院,甘肃 兰州 730000%甘肃省人民医院泌尿外科干部病区,甘肃 兰州 730000
28.01.2025
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0577-7402 |
| DOI | 10.11855/j.issn.0577-7402.0390.2024.1015 |
Cover
| Abstract | R737.25; 目的 探讨基于磁共振成像(MRI)的前列腺癌(PCa)瘤内及瘤周影像组学对骨转移的诊断价值.方法 收集2018年1月-2023年1月在甘肃省人民医院经组织穿刺病理学检查确诊为PCa的211例患者的临床资料进行回顾性分析.将患者按照7:3的比例随机分为训练集(n=147)与验证集(n=64);分别从患者的T2加权成像(T2WI)、扩散加权成像(DWI)及扩散系数成像(ADC)3个序列勾画感兴趣区(ROIs),用于提取影像组学特征;使用Z-score(正则化)、LASSO算法进行影像组学特征的降维、选择、构建;然后基于逻辑回归(LR)机器学习分类器构建模型;绘制受试者操作特征(ROC)曲线并计算曲线下面积(AUC),评估模型的效能;绘制校准曲线和决策曲线(DCA)评价模型的拟合度及临床净获益.结果 从T2WI、DWI和ADC中分别提取瘤内和瘤周影像组学特征各312个.使用LASSO回归模型最终筛选出与骨转移密切相关的瘤内影像组学特征10个(包括2个T2序列特征、7个DWI特征、1个ADC序列特征)及瘤周影像组学特征9个(包括4个T2序列特征、3个DWI特征、2个ADC序列特征).基于瘤内影像组学特征构建的模型在验证集中AUC为0.845(95%CI 0.747～0.943),基于瘤周影像组学特征构建的模型在验证集中AUC为0.818(95%CI 0.716～0.919);基于瘤内、瘤周影像组学特征及临床特征(包括Gleason评分、总前列腺特异性抗原、体重指数)构建的联合模型(列线图)的AUC为0.936(95%CI 0.902～0.970);校准曲线表明联合模型具有良好的拟合度,DCA表明联合模型具有更好的临床净获益.结论 瘤周影像组学对于初诊PCa骨转移有较高的诊断价值,且结合瘤内影像组学特征及临床特征可明显提高模型的诊断能力. |
|---|---|
| AbstractList | R737.25; 目的 探讨基于磁共振成像(MRI)的前列腺癌(PCa)瘤内及瘤周影像组学对骨转移的诊断价值.方法 收集2018年1月-2023年1月在甘肃省人民医院经组织穿刺病理学检查确诊为PCa的211例患者的临床资料进行回顾性分析.将患者按照7:3的比例随机分为训练集(n=147)与验证集(n=64);分别从患者的T2加权成像(T2WI)、扩散加权成像(DWI)及扩散系数成像(ADC)3个序列勾画感兴趣区(ROIs),用于提取影像组学特征;使用Z-score(正则化)、LASSO算法进行影像组学特征的降维、选择、构建;然后基于逻辑回归(LR)机器学习分类器构建模型;绘制受试者操作特征(ROC)曲线并计算曲线下面积(AUC),评估模型的效能;绘制校准曲线和决策曲线(DCA)评价模型的拟合度及临床净获益.结果 从T2WI、DWI和ADC中分别提取瘤内和瘤周影像组学特征各312个.使用LASSO回归模型最终筛选出与骨转移密切相关的瘤内影像组学特征10个(包括2个T2序列特征、7个DWI特征、1个ADC序列特征)及瘤周影像组学特征9个(包括4个T2序列特征、3个DWI特征、2个ADC序列特征).基于瘤内影像组学特征构建的模型在验证集中AUC为0.845(95%CI 0.747～0.943),基于瘤周影像组学特征构建的模型在验证集中AUC为0.818(95%CI 0.716～0.919);基于瘤内、瘤周影像组学特征及临床特征(包括Gleason评分、总前列腺特异性抗原、体重指数)构建的联合模型(列线图)的AUC为0.936(95%CI 0.902～0.970);校准曲线表明联合模型具有良好的拟合度,DCA表明联合模型具有更好的临床净获益.结论 瘤周影像组学对于初诊PCa骨转移有较高的诊断价值,且结合瘤内影像组学特征及临床特征可明显提高模型的诊断能力. |
| Abstract_FL | Objective To investigate the diagnostic value of magnetic resonance imaging(MRI)-based intratumoral and peritumoral radiomics of prostate cancer(PCa)for bone metastases.Methods A total of 211 patients diagnosed with PCa by biopsy pathology at Gansu Provincial People's Hospital from January 2018 to January 2023 were retrospectively analyzed.These patients were randomly divided into a training set(n=147)and a validation set(n=64)in a 7:3 ratio.Regions of interest(ROIs)were delineated from the patients'T2-weighted imaging(T2WI),diffusion-weighted imaging(DWI),and apparent diffusion coefficient imaging(ADC)sequences to extract radiomic features.Z-score(normalization)and the LASSO algorithm were used for feature dimensionality reduction,selection,and construction.A predictive model was then built using a logistic regression(LR)machine learning classifier.The receiver operating characteristic(ROC)curve was plotted,and the area under the curve(AUC)was calculated to assess the model's performance.Calibration curves and decision curves(DCA)were plotted to evaluate the model's fit and clinical net benefit.Results Radiomic features were extracted from the tumor and peritumoral regions in each patient's T2WI,DWI,and ADC images,with a total of 312 features from each region.The LASSO regression model ultimately identified 10 intratumoral radiomic features closely related to bone metastasis,including 2 T2 sequence features,7 DWI features,and 1 ADC sequence feature;and 9 peritumoral radiomic features,including 4 T2 sequence features,3 DWI features,and 2 ADC sequence features.The predictive model based on intratumoral radiomic features achieved an AUC of 0.845(95%CI 0.747-0.943),while the predictive model based on peritumoral radiomic features had an AUC of 0.818(95%CI 0.716-0.919).A combined nomogram model incorporating intratumoral features,peritumoral radiomic features,and clinical features(including Gleason score,total prostate specific antigen,and body mass index)yielded an AUC of 0.936(95%CI 0.902-0.970).Calibration curves indicated that the combined model had good fit,and DCA demonstrated that the combined model provided better clinical net benefit.Conclusions Peritumoral radiomics has excellent predictive value for bone metastasis in newly diagnosed PCa.Combining with intratumoral radiomics features and clinical features,it significantly enhances the predictive capability of the model. |
| Author | 张云峰 何涵 周逢海 杨志军 杨进 苗国良 |
| AuthorAffiliation | 甘肃中医药大学第一临床医学院,甘肃 兰州 730000%兰州大学第一临床医学院,甘肃 兰州 730000%甘肃省人民医院泌尿外科干部病区,甘肃 兰州 730000 |
| AuthorAffiliation_xml | – name: 甘肃中医药大学第一临床医学院,甘肃 兰州 730000%兰州大学第一临床医学院,甘肃 兰州 730000%甘肃省人民医院泌尿外科干部病区,甘肃 兰州 730000 |
| Author_FL | He Han Zhang Yun-Feng Yang Jin Zhou Feng-Hai Miao Guo-Liang Yang Zhi-Jun |
| Author_FL_xml | – sequence: 1 fullname: Zhang Yun-Feng – sequence: 2 fullname: Yang Zhi-Jun – sequence: 3 fullname: Yang Jin – sequence: 4 fullname: Miao Guo-Liang – sequence: 5 fullname: He Han – sequence: 6 fullname: Zhou Feng-Hai |
| Author_xml | – sequence: 1 fullname: 张云峰 – sequence: 2 fullname: 杨志军 – sequence: 3 fullname: 杨进 – sequence: 4 fullname: 苗国良 – sequence: 5 fullname: 何涵 – sequence: 6 fullname: 周逢海 |
| BookMark | eNo9j01Lw0AYhPdQwVr7P3pJfN_dbHZ7lFK1UBFEz2XzJQ2SgkHUngRb0aIUL36dRYtYiifR2H_jmvgvjCjOZQYGZnjmSCHqRD4hFQQTUXK-EJrtOI5M4EIYwgJqAquCSYFaJgLyAin-V7OkHMdtBwARLAvtIqnr03N9cpX139Kbs_T6Th_39XDwEy5Gq-sNPX3WR8M06enxvZ68fj2OsulT-pCkt71sMvi8HH8kL_rwfZ7MBGo79st_XiKbS_WN2orRXFtu1BabRozA0BC2pEpRxSU4TPoSmAg8V1Duc3Rd10cLPR-dai7FGJPgMcWpbXGXKs_mkpVI5Xd3T0WBirZaYWd3J8ofW2EQHux3uzk1B8z52DfwFmmC |
| ClassificationCodes | R737.25 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.11855/j.issn.0577-7402.0390.2024.1015 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| DocumentTitle_FL | Diagnostic value of intratumoral and peritumoral MRI radiomics for bone metastasis in prostate cancer |
| EndPage | 8 |
| ExternalDocumentID | jfjyxzz202501001 |
| GroupedDBID | -05 2B. 4A8 5VS 5XA 5XF 92F 92I 93N ABUWG ACGFS AFKRA ALMA_UNASSIGNED_HOLDINGS BENPR BPHCQ BVBZV CCEZO CCPQU CIEJG CW9 IPNFZ KQ8 PQQKQ PROAC PSX RIG RNS TCJ TGQ U1G U5O |
| ID | FETCH-LOGICAL-s1031-7682aa2a580b38e8037fdc725e51ccce141de1b9999a33380d3a52645c2ad6583 |
| ISSN | 0577-7402 |
| IngestDate | Thu May 29 04:00:08 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Keywords | 前列腺癌 骨转移 prostate cancer 机器学习 bone metastases peritumoral radiomics machine learning 瘤周影像组学 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1031-7682aa2a580b38e8037fdc725e51ccce141de1b9999a33380d3a52645c2ad6583 |
| PageCount | 8 |
| ParticipantIDs | wanfang_journals_jfjyxzz202501001 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-01-28 |
| PublicationDateYYYYMMDD | 2025-01-28 |
| PublicationDate_xml | – month: 01 year: 2025 text: 2025-01-28 day: 28 |
| PublicationDecade | 2020 |
| PublicationTitle | 解放军医学杂志 |
| PublicationTitle_FL | Medical Journal of Chinese People's Liberation Army |
| PublicationYear | 2025 |
| Publisher | 甘肃中医药大学第一临床医学院,甘肃 兰州 730000%兰州大学第一临床医学院,甘肃 兰州 730000%甘肃省人民医院泌尿外科干部病区,甘肃 兰州 730000 |
| Publisher_xml | – name: 甘肃中医药大学第一临床医学院,甘肃 兰州 730000%兰州大学第一临床医学院,甘肃 兰州 730000%甘肃省人民医院泌尿外科干部病区,甘肃 兰州 730000 |
| SSID | ssib001104416 ssib002263991 ssib046619461 ssib051375714 ssj0058562 ssib038074682 ssib052002838 |
| Score | 2.3949661 |
| Snippet | R737.25; 目的 探讨基于磁共振成像(MRI)的前列腺癌(PCa)瘤内及瘤周影像组学对骨转移的诊断价值.方法... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 1 |
| Title | 前列腺癌瘤内及瘤周MRI影像组学对骨转移的诊断价值 |
| URI | https://d.wanfangdata.com.cn/periodical/jfjyxzz202501001 |
| Volume | 50 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwzR1NaxQxdKgtFC_iJ37TggGhzJqZSSbJMbM7SxVapLTQW5mZ3VV6WMG2oHsSbEWLUrz4dRYtYimeRGv_jePWf-F72ezs6hZsPXlZHsn7fm-SvNlk4jhXskSIWpB6bqLCzGVhPXNTxrlLG2HK0lpKffN3wdR0ODnHbszz-aGR8b5dSyvLaSlr7Xuu5F-iCm0QVzwle4jIFkyhAWCIL_xChOH3QDEmMSdSEVkxgCRKkFgSyUmkSSyIgq6yASTRzOCE2ItAlUj9W5fyiJZTM9cRjiok8gxagJiAFkVEGjRdITo0QJVEisSKaA2EKBeotBGnDT4y14ZKIjKKC4kKkUPMECESRgQl9nbtxa5REjnowOADZmw1V5EByoZ5oQm0V4j0jdpVoopp1TSUiaZGmkb7sCUgEe2hGGLU3hIXkvZBkQalrwc8HVkaUA2sxxbwR7X_TYqPmxa7J9Mx941fGPod0X10MSoojV8K8yQGFbyGdjJ0R89ggV5GRxsqSS0QmfCAoejoQTcpzAbtwxM1qMCEIQBialhAdzyBFwzgBd58sO-_UGrQidBShrrIhjsy6QbEnbhbyV2B2BWYh8MIiLqOVqHNX5stikQ-UgF_TAGB4bYPUBlFHE7xvkmXC-EKRn9bIXA6MBJ2pnuvf924_4JEcm5WJMi9VHAv0UDREiQhw9dnvLcYK7bILjYW799rtTBPKX4n7Ygz4guBO1FGonj65kyv5vEo6986APUUFB3FpI0XSrCw9wErFuJ7y95hdu4FgoveVgr8DJtvtlJ0lrNccnMrc6H6qHO1a9i1v5hlDkI2G0nzVt-affa4c8wW22O6M3KecIZat086o1N2O9EpJ86fPMsfv9xb-9p-_bT96m3-aC3fWEfg-SYMhfnup_zhRntnNd96l29_-flhc2_3Y_v9TvvN6t72-o8XW993PucPvp125qrxbHnStffKuEt4qY0rwB1J4idc0jSQdUkD0ahlwud17mVZVveYV6t7KZTOKgkCcGAtSDgUjjzzkxpUbMEZZ7h5p1k_64xhvQkVMhTBHMoBylIpVUMGrJE0gDTLzjnj1gMLdt5YWvgzsucPgHPBOdobsS46w8t3V-qXoBpaTi_bfPgFDTz1xw |
| linkProvider | ProQuest |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%89%8D%E5%88%97%E8%85%BA%E7%99%8C%E7%98%A4%E5%86%85%E5%8F%8A%E7%98%A4%E5%91%A8MRI%E5%BD%B1%E5%83%8F%E7%BB%84%E5%AD%A6%E5%AF%B9%E9%AA%A8%E8%BD%AC%E7%A7%BB%E7%9A%84%E8%AF%8A%E6%96%AD%E4%BB%B7%E5%80%BC&rft.jtitle=%E8%A7%A3%E6%94%BE%E5%86%9B%E5%8C%BB%E5%AD%A6%E6%9D%82%E5%BF%97&rft.au=%E5%BC%A0%E4%BA%91%E5%B3%B0&rft.au=%E6%9D%A8%E5%BF%97%E5%86%9B&rft.au=%E6%9D%A8%E8%BF%9B&rft.au=%E8%8B%97%E5%9B%BD%E8%89%AF&rft.date=2025-01-28&rft.pub=%E7%94%98%E8%82%83%E4%B8%AD%E5%8C%BB%E8%8D%AF%E5%A4%A7%E5%AD%A6%E7%AC%AC%E4%B8%80%E4%B8%B4%E5%BA%8A%E5%8C%BB%E5%AD%A6%E9%99%A2%2C%E7%94%98%E8%82%83+%E5%85%B0%E5%B7%9E+730000%25%E5%85%B0%E5%B7%9E%E5%A4%A7%E5%AD%A6%E7%AC%AC%E4%B8%80%E4%B8%B4%E5%BA%8A%E5%8C%BB%E5%AD%A6%E9%99%A2%2C%E7%94%98%E8%82%83+%E5%85%B0%E5%B7%9E+730000%25%E7%94%98%E8%82%83%E7%9C%81%E4%BA%BA%E6%B0%91%E5%8C%BB%E9%99%A2%E6%B3%8C%E5%B0%BF%E5%A4%96%E7%A7%91%E5%B9%B2%E9%83%A8%E7%97%85%E5%8C%BA%2C%E7%94%98%E8%82%83+%E5%85%B0%E5%B7%9E+730000&rft.issn=0577-7402&rft.volume=50&rft.issue=1&rft.spage=1&rft.epage=8&rft_id=info:doi/10.11855%2Fj.issn.0577-7402.0390.2024.1015&rft.externalDocID=jfjyxzz202501001 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fjfjyxzz%2Fjfjyxzz.jpg |