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<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.</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<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.</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}
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.
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.