心外膜脂肪组织放射组学特征对检测 COVID-19 感染严重程度的增量价值

IF 0.5 4区 医学 Q4 CARDIAC & CARDIOVASCULAR SYSTEMS Kardiologiya Pub Date : 2024-09-30 DOI:10.18087/cardio.2024.9.n2685
Ni Yao, Yanhui Tian, Daniel Gama das Neves, Chen Zhao, Claudio Tinoco Mesquita, Wolney de Andrade Martins, Alair Augusto Sarmet Moreira Damas Dos Santos, Yanting Li, Chuang Han, Fubao Zhu, Neng Dai, Weihua Zhou
{"title":"心外膜脂肪组织放射组学特征对检测 COVID-19 感染严重程度的增量价值","authors":"Ni Yao, Yanhui Tian, Daniel Gama das Neves, Chen Zhao, Claudio Tinoco Mesquita, Wolney de Andrade Martins, Alair Augusto Sarmet Moreira Damas Dos Santos, Yanting Li, Chuang Han, Fubao Zhu, Neng Dai, Weihua Zhou","doi":"10.18087/cardio.2024.9.n2685","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Epicardial adipose tissue (EAT) is known for its pro-inflammatory properties and association with Coronavirus Disease 2019 (COVID-19) severity. However, existing detection methods for COVID-19 severity assessment often lack consideration of organs and tissues other than the lungs, which limits the accuracy and reliability of these predictive models.</p><p><strong>Material and methods: </strong>The retrospective study included data from 515 COVID-19 patients (Cohort 1, n=415; Cohort 2, n=100) from two centers (Shanghai Public Health Center and Brazil Niteroi Hospital) between January 2020 and July 2020. Firstly, a three-stage EAT segmentation method was proposed by combining object detection and segmentation networks. Lung and EAT radiomics features were then extracted, and feature selection was performed. Finally, a hybrid model, based on seven machine learning models, was built for detecting COVID-19 severity. The hybrid model's performance and uncertainty were evaluated in both internal and external validation cohorts.</p><p><strong>Results: </strong>For EAT extraction, the Dice similarity coefficients (DSC) of the two centers were 0.972 (±0.011) and 0.968 (±0.005), respectively. For severity detection, the area under the receiver operating characteristic curve (AUC), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) of the hybrid model increased by 0.09 (p&lt;0.001), 19.3 % (p&lt;0.05), and 18.0 % (p&lt;0.05) in the internal validation cohort, and by 0.06 (p&lt;0.001), 18.0 % (p&lt;0.05) and 18.0 % (p&lt;0.05) in the external validation cohort, respectively. Uncertainty and radiomics features analysis confirmed the interpretability of increased certainty in case prediction after inclusion of EAT features.</p><p><strong>Conclusion: </strong>This study proposed a novel three-stage EAT extraction method. We demonstrated that adding EAT radiomics features to a COVID-19 severity detection model results in increased accuracy and reduced uncertainty. The value of these features was also confirmed through feature importance ranking and visualization.</p>","PeriodicalId":54750,"journal":{"name":"Kardiologiya","volume":null,"pages":null},"PeriodicalIF":0.5000,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Incremental Value of Radiomics Features of Epicardial Adipose Tissue for Detecting the Severity of COVID-19 Infection.\",\"authors\":\"Ni Yao, Yanhui Tian, Daniel Gama das Neves, Chen Zhao, Claudio Tinoco Mesquita, Wolney de Andrade Martins, Alair Augusto Sarmet Moreira Damas Dos Santos, Yanting Li, Chuang Han, Fubao Zhu, Neng Dai, Weihua Zhou\",\"doi\":\"10.18087/cardio.2024.9.n2685\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction: </strong>Epicardial adipose tissue (EAT) is known for its pro-inflammatory properties and association with Coronavirus Disease 2019 (COVID-19) severity. However, existing detection methods for COVID-19 severity assessment often lack consideration of organs and tissues other than the lungs, which limits the accuracy and reliability of these predictive models.</p><p><strong>Material and methods: </strong>The retrospective study included data from 515 COVID-19 patients (Cohort 1, n=415; Cohort 2, n=100) from two centers (Shanghai Public Health Center and Brazil Niteroi Hospital) between January 2020 and July 2020. Firstly, a three-stage EAT segmentation method was proposed by combining object detection and segmentation networks. Lung and EAT radiomics features were then extracted, and feature selection was performed. Finally, a hybrid model, based on seven machine learning models, was built for detecting COVID-19 severity. The hybrid model's performance and uncertainty were evaluated in both internal and external validation cohorts.</p><p><strong>Results: </strong>For EAT extraction, the Dice similarity coefficients (DSC) of the two centers were 0.972 (±0.011) and 0.968 (±0.005), respectively. For severity detection, the area under the receiver operating characteristic curve (AUC), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) of the hybrid model increased by 0.09 (p&lt;0.001), 19.3 % (p&lt;0.05), and 18.0 % (p&lt;0.05) in the internal validation cohort, and by 0.06 (p&lt;0.001), 18.0 % (p&lt;0.05) and 18.0 % (p&lt;0.05) in the external validation cohort, respectively. Uncertainty and radiomics features analysis confirmed the interpretability of increased certainty in case prediction after inclusion of EAT features.</p><p><strong>Conclusion: </strong>This study proposed a novel three-stage EAT extraction method. We demonstrated that adding EAT radiomics features to a COVID-19 severity detection model results in increased accuracy and reduced uncertainty. The value of these features was also confirmed through feature importance ranking and visualization.</p>\",\"PeriodicalId\":54750,\"journal\":{\"name\":\"Kardiologiya\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.5000,\"publicationDate\":\"2024-09-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Kardiologiya\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.18087/cardio.2024.9.n2685\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"CARDIAC & CARDIOVASCULAR SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Kardiologiya","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.18087/cardio.2024.9.n2685","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

导言:心外膜脂肪组织(EAT)因其促炎特性和与冠状病毒疾病2019(COVID-19)严重程度相关而闻名。然而,现有的用于评估 COVID-19 严重程度的检测方法往往缺乏对肺部以外器官和组织的考虑,这限制了这些预测模型的准确性和可靠性:该回顾性研究纳入了2020年1月至2020年7月期间来自两个中心(上海公共卫生中心和巴西尼泰罗伊医院)的515名COVID-19患者(队列1,n=415;队列2,n=100)的数据。首先,结合物体检测和分割网络,提出了三阶段 EAT 分割方法。然后提取肺和 EAT 放射组学特征,并进行特征选择。最后,建立了一个基于七个机器学习模型的混合模型,用于检测 COVID-19 的严重程度。在内部和外部验证队列中对混合模型的性能和不确定性进行了评估:结果:在EAT提取方面,两个中心的Dice相似系数(DSC)分别为0.972(±0.011)和0.968(±0.005)。在严重程度检测方面,混合模型的接收者操作特征曲线下面积(AUC)、净再分类改进(NRI)和综合辨别改进(IDI)分别增加了 0.在内部验证队列中分别增加了 0.09 (p<0.001)、19.3 % (p<0.05) 和 18.0 % (p<0.05),在外部验证队列中分别增加了 0.06 (p<0.001)、18.0 % (p<0.05) 和 18.0 % (p<0.05)。不确定性和放射组学特征分析证实,纳入 EAT 特征后,病例预测的确定性增加了:本研究提出了一种新颖的三阶段 EAT 提取方法。我们证明,在 COVID-19 严重程度检测模型中加入 EAT 放射组学特征可提高准确性并降低不确定性。这些特征的价值还通过特征重要性排序和可视化得到了证实。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Incremental Value of Radiomics Features of Epicardial Adipose Tissue for Detecting the Severity of COVID-19 Infection.

Introduction: Epicardial adipose tissue (EAT) is known for its pro-inflammatory properties and association with Coronavirus Disease 2019 (COVID-19) severity. However, existing detection methods for COVID-19 severity assessment often lack consideration of organs and tissues other than the lungs, which limits the accuracy and reliability of these predictive models.

Material and methods: The retrospective study included data from 515 COVID-19 patients (Cohort 1, n=415; Cohort 2, n=100) from two centers (Shanghai Public Health Center and Brazil Niteroi Hospital) between January 2020 and July 2020. Firstly, a three-stage EAT segmentation method was proposed by combining object detection and segmentation networks. Lung and EAT radiomics features were then extracted, and feature selection was performed. Finally, a hybrid model, based on seven machine learning models, was built for detecting COVID-19 severity. The hybrid model's performance and uncertainty were evaluated in both internal and external validation cohorts.

Results: For EAT extraction, the Dice similarity coefficients (DSC) of the two centers were 0.972 (±0.011) and 0.968 (±0.005), respectively. For severity detection, the area under the receiver operating characteristic curve (AUC), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) of the hybrid model increased by 0.09 (p<0.001), 19.3 % (p<0.05), and 18.0 % (p<0.05) in the internal validation cohort, and by 0.06 (p<0.001), 18.0 % (p<0.05) and 18.0 % (p<0.05) in the external validation cohort, respectively. Uncertainty and radiomics features analysis confirmed the interpretability of increased certainty in case prediction after inclusion of EAT features.

Conclusion: This study proposed a novel three-stage EAT extraction method. We demonstrated that adding EAT radiomics features to a COVID-19 severity detection model results in increased accuracy and reduced uncertainty. The value of these features was also confirmed through feature importance ranking and visualization.

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
Kardiologiya
Kardiologiya 医学-心血管系统
CiteScore
1.70
自引率
20.00%
发文量
94
审稿时长
3-8 weeks
期刊介绍: “Kardiologiya” (Cardiology) is a monthly scientific, peer-reviewed journal committed to both basic cardiovascular medicine and practical aspects of cardiology. As the leader in its field, “Kardiologiya” provides original coverage of recent progress in cardiovascular medicine. We publish state-of-the-art articles integrating clinical and research activities in the fields of basic cardiovascular science and clinical cardiology, with a focus on emerging issues in cardiovascular disease. Our target audience spans a diversity of health care professionals and medical researchers working in cardiovascular medicine and related fields. The principal language of the Journal is Russian, an additional language – English (title, authors’ information, abstract, keywords). “Kardiologiya” is a peer-reviewed scientific journal. All articles are reviewed by scientists, who gained high international prestige in cardiovascular science and clinical cardiology. The Journal is currently cited and indexed in major Abstracting & Indexing databases: Web of Science, Medline and Scopus. The Journal''s primary objectives Contribute to raising the professional level of medical researchers, physicians and academic teachers. Present the results of current research and clinical observations, explore the effectiveness of drug and non-drug treatments of heart disease, inform about new diagnostic techniques; discuss current trends and new advancements in clinical cardiology, contribute to continuing medical education, inform readers about results of Russian and international scientific forums; Further improve the general quality of reviewing and editing of manuscripts submitted for publication; Provide the widest possible dissemination of the published articles, among the global scientific community; Extend distribution and indexing of scientific publications in major Abstracting & Indexing databases.
期刊最新文献
Assessment of Specific Biomarkers' Profile and Structural, Functional Parameters of the Left Ventricle in Patients With Lymphomas Undergoing Antitumor Therapy. Comparative Analysis of The Effectiveness of Antihypertensive Therapy Including Spironolactone and Eplerenone in Patients With Essential Hypertension and Atrial Fibrillation. Effects of Ventricular Extrasystoles on Right Ventricle Functions (a Speckle Tracking Study). VES and RV Strain Imaging. In Search of Optimal Criteria for Iron Deficiency in CHF Patients. Post-hoc Analysis of the Study "Prevalence of Iron Deficiency in Patients With Chronic Heart Failure in the Russian Federation (ID-CHF-RF)". Incremental Value of Radiomics Features of Epicardial Adipose Tissue for Detecting the Severity of COVID-19 Infection.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1