基于ct的放射组学模型在预测肝泡包虫病的微血管密度中的应用。

IF 2.9 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Juan Hou, Simiao Zhang, Shouxian Li, Zicheng Zhao, Longfei Zhao, Tieliang Zhang, Wenya Liu
{"title":"基于ct的放射组学模型在预测肝泡包虫病的微血管密度中的应用。","authors":"Juan Hou, Simiao Zhang, Shouxian Li, Zicheng Zhao, Longfei Zhao, Tieliang Zhang, Wenya Liu","doi":"10.1186/s12880-025-01612-5","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the performance of CT-based intralesional combined with different perilesional radiomics models in predicting the microvascular density (MVD) of hepatic alveolar echinococcosis (HAE).</p><p><strong>Methods: </strong>This study retrospectively analyzed preoperative CT data from 303 patients with HAE confirmed by surgical pathology (MVD positive, n = 182; MVD negative, n = 121). The patients were randomly divided into the training cohort (n = 242) and test cohort (n = 61) at a ratio of 8:2. The radiomics features were extracted from CT images on the portal vein phase. Four radiomics models were constructed based on gross lesion volume (GLV), gross combined 10 mm perilesional volume (GPLV<sub>10mm</sub>), gross combined 15 mm perilesional volume (GPLV<sub>15mm</sub>) and gross combined 20 mm perilesional volume (GPLV<sub>20mm</sub>). The best radiomics signature model and clinical features were combined to establish a nomogram. Receiver operating characteristic curve (ROC) and decision curve analysis (DCA) were used to evaluate the predictive performance of models.</p><p><strong>Results: </strong>Among the four radiomics models, the GPLV<sub>20mm</sub> model performed the highest prediction performance with the area under the curves (AUCs) in training cohort and test cohort was 0.876 and 0.802, respectively. The AUC of the clinical model was 0.753 in the training cohort and 0.699 in the test cohort. The AUC of the nomogram model based clinical and GPLV<sub>20mm</sub> radiomic signatures was 0.922 in the training cohort and 0.849 in the test cohort. The DCA showed that the nomogram had greater benefits among the three models.</p><p><strong>Conclusion: </strong>CT-based GPLV<sub>20mm</sub> radiomics model can better predict MVD of HAE. The nomogram model showed the best predictive performance.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"84"},"PeriodicalIF":2.9000,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11895365/pdf/","citationCount":"0","resultStr":"{\"title\":\"CT-based radiomics models using intralesional and different perilesional signatures in predicting the microvascular density of hepatic alveolar echinococcosis.\",\"authors\":\"Juan Hou, Simiao Zhang, Shouxian Li, Zicheng Zhao, Longfei Zhao, Tieliang Zhang, Wenya Liu\",\"doi\":\"10.1186/s12880-025-01612-5\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objectives: </strong>To evaluate the performance of CT-based intralesional combined with different perilesional radiomics models in predicting the microvascular density (MVD) of hepatic alveolar echinococcosis (HAE).</p><p><strong>Methods: </strong>This study retrospectively analyzed preoperative CT data from 303 patients with HAE confirmed by surgical pathology (MVD positive, n = 182; MVD negative, n = 121). The patients were randomly divided into the training cohort (n = 242) and test cohort (n = 61) at a ratio of 8:2. The radiomics features were extracted from CT images on the portal vein phase. Four radiomics models were constructed based on gross lesion volume (GLV), gross combined 10 mm perilesional volume (GPLV<sub>10mm</sub>), gross combined 15 mm perilesional volume (GPLV<sub>15mm</sub>) and gross combined 20 mm perilesional volume (GPLV<sub>20mm</sub>). The best radiomics signature model and clinical features were combined to establish a nomogram. Receiver operating characteristic curve (ROC) and decision curve analysis (DCA) were used to evaluate the predictive performance of models.</p><p><strong>Results: </strong>Among the four radiomics models, the GPLV<sub>20mm</sub> model performed the highest prediction performance with the area under the curves (AUCs) in training cohort and test cohort was 0.876 and 0.802, respectively. The AUC of the clinical model was 0.753 in the training cohort and 0.699 in the test cohort. The AUC of the nomogram model based clinical and GPLV<sub>20mm</sub> radiomic signatures was 0.922 in the training cohort and 0.849 in the test cohort. The DCA showed that the nomogram had greater benefits among the three models.</p><p><strong>Conclusion: </strong>CT-based GPLV<sub>20mm</sub> radiomics model can better predict MVD of HAE. The nomogram model showed the best predictive performance.</p>\",\"PeriodicalId\":9020,\"journal\":{\"name\":\"BMC Medical Imaging\",\"volume\":\"25 1\",\"pages\":\"84\"},\"PeriodicalIF\":2.9000,\"publicationDate\":\"2025-03-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11895365/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BMC Medical Imaging\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s12880-025-01612-5\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Medical Imaging","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12880-025-01612-5","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

摘要

目的:评价基于ct的病灶内结合不同病灶周围放射组学模型预测肝肺泡包虫病(HAE)微血管密度(MVD)的效果。方法:本研究回顾性分析手术病理证实的303例HAE患者的术前CT资料(MVD阳性,182例;MVD阴性,n = 121)。将患者按8:2的比例随机分为训练组(n = 242)和测试组(n = 61)。从门静脉期CT图像中提取放射组学特征。基于病灶总体积(GLV)、病灶总合并10mm周围体积(GPLV10mm)、病灶总合并15mm周围体积(GPLV15mm)和病灶总合并20mm周围体积(GPLV20mm)构建4个放射组学模型。将最佳放射组学特征模型与临床特征相结合建立nomogram。采用受试者工作特征曲线(ROC)和决策曲线分析(DCA)评价模型的预测性能。结果:四种放射组学模型中,GPLV20mm模型预测效果最好,训练组和测试组的曲线下面积(auc)分别为0.876和0.802。临床模型在训练组的AUC为0.753,在测试组的AUC为0.699。基于nomogram模型的临床和GPLV20mm放射学特征AUC在训练组为0.922,在测试组为0.849。DCA结果表明,三种模型中,nomogram具有更大的效益。结论:基于ct的GPLV20mm放射组学模型能较好地预测HAE的MVD。模态图模型的预测效果最好。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
CT-based radiomics models using intralesional and different perilesional signatures in predicting the microvascular density of hepatic alveolar echinococcosis.

Objectives: To evaluate the performance of CT-based intralesional combined with different perilesional radiomics models in predicting the microvascular density (MVD) of hepatic alveolar echinococcosis (HAE).

Methods: This study retrospectively analyzed preoperative CT data from 303 patients with HAE confirmed by surgical pathology (MVD positive, n = 182; MVD negative, n = 121). The patients were randomly divided into the training cohort (n = 242) and test cohort (n = 61) at a ratio of 8:2. The radiomics features were extracted from CT images on the portal vein phase. Four radiomics models were constructed based on gross lesion volume (GLV), gross combined 10 mm perilesional volume (GPLV10mm), gross combined 15 mm perilesional volume (GPLV15mm) and gross combined 20 mm perilesional volume (GPLV20mm). The best radiomics signature model and clinical features were combined to establish a nomogram. Receiver operating characteristic curve (ROC) and decision curve analysis (DCA) were used to evaluate the predictive performance of models.

Results: Among the four radiomics models, the GPLV20mm model performed the highest prediction performance with the area under the curves (AUCs) in training cohort and test cohort was 0.876 and 0.802, respectively. The AUC of the clinical model was 0.753 in the training cohort and 0.699 in the test cohort. The AUC of the nomogram model based clinical and GPLV20mm radiomic signatures was 0.922 in the training cohort and 0.849 in the test cohort. The DCA showed that the nomogram had greater benefits among the three models.

Conclusion: CT-based GPLV20mm radiomics model can better predict MVD of HAE. The nomogram model showed the best predictive performance.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
BMC Medical Imaging
BMC Medical Imaging RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING-
CiteScore
4.60
自引率
3.70%
发文量
198
审稿时长
27 weeks
期刊介绍: BMC Medical Imaging is an open access journal publishing original peer-reviewed research articles in the development, evaluation, and use of imaging techniques and image processing tools to diagnose and manage disease.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信