用于预测 CT 检测到的肺结节恶性风险的深度学习模型:系统综述与元分析》。

IF 4.6 2区 医学 Q1 RESPIRATORY SYSTEM
Lung Pub Date : 2024-10-01 Epub Date: 2024-05-23 DOI:10.1007/s00408-024-00706-1
Wahyu Wulaningsih, Carmela Villamaria, Abdullah Akram, Janella Benemile, Filippo Croce, Johnathan Watkins
{"title":"用于预测 CT 检测到的肺结节恶性风险的深度学习模型:系统综述与元分析》。","authors":"Wahyu Wulaningsih, Carmela Villamaria, Abdullah Akram, Janella Benemile, Filippo Croce, Johnathan Watkins","doi":"10.1007/s00408-024-00706-1","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>There has been growing interest in using artificial intelligence/deep learning (DL) to help diagnose prevalent diseases earlier. In this study we sought to survey the landscape of externally validated DL-based computer-aided diagnostic (CADx) models, and assess their diagnostic performance for predicting the risk of malignancy in computed tomography (CT)-detected pulmonary nodules.</p><p><strong>Methods: </strong>An electronic search was performed in four databases (from inception to 10 August 2023). Studies were eligible if they were peer-reviewed experimental or observational articles comparing the diagnostic performance of externally validated DL-based CADx models with models widely used in clinical practice to predict the risk of malignancy. A bivariate random-effect approach for the meta-analysis on the included studies was used.</p><p><strong>Results: </strong>Seventeen studies were included, comprising 8553 participants and 9884 nodules. Pooled analyses showed DL-based CADx models were 11.6% more sensitive than physician judgement alone, and 14.5% more than clinical risk models alone. They had a similar pooled specificity to physician judgement alone [0.77 (95% CI 0.68-0.84) v 0.81 (95% CI 0.71-0.88)], and were 7.4% more specific than clinical risk models alone. They had superior pooled areas under the receiver operating curve (AUC), with relative pooled AUCs of 1.03 (95% CI 1.00-1.07) and 1.10 (95% CI 1.07-1.13) versus physician judgement and clinical risk models alone, respectively.</p><p><strong>Conclusion: </strong>DL-based models are already used in clinical practice in certain settings for nodule management. Our results show their diagnostic performance potentially justifies wider, more routine deployment alongside experienced physician readers to help inform multidisciplinary team decision-making.</p>","PeriodicalId":18163,"journal":{"name":"Lung","volume":null,"pages":null},"PeriodicalIF":4.6000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11427562/pdf/","citationCount":"0","resultStr":"{\"title\":\"Deep Learning Models for Predicting Malignancy Risk in CT-Detected Pulmonary Nodules: A Systematic Review and Meta-analysis.\",\"authors\":\"Wahyu Wulaningsih, Carmela Villamaria, Abdullah Akram, Janella Benemile, Filippo Croce, Johnathan Watkins\",\"doi\":\"10.1007/s00408-024-00706-1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>There has been growing interest in using artificial intelligence/deep learning (DL) to help diagnose prevalent diseases earlier. In this study we sought to survey the landscape of externally validated DL-based computer-aided diagnostic (CADx) models, and assess their diagnostic performance for predicting the risk of malignancy in computed tomography (CT)-detected pulmonary nodules.</p><p><strong>Methods: </strong>An electronic search was performed in four databases (from inception to 10 August 2023). Studies were eligible if they were peer-reviewed experimental or observational articles comparing the diagnostic performance of externally validated DL-based CADx models with models widely used in clinical practice to predict the risk of malignancy. A bivariate random-effect approach for the meta-analysis on the included studies was used.</p><p><strong>Results: </strong>Seventeen studies were included, comprising 8553 participants and 9884 nodules. Pooled analyses showed DL-based CADx models were 11.6% more sensitive than physician judgement alone, and 14.5% more than clinical risk models alone. They had a similar pooled specificity to physician judgement alone [0.77 (95% CI 0.68-0.84) v 0.81 (95% CI 0.71-0.88)], and were 7.4% more specific than clinical risk models alone. They had superior pooled areas under the receiver operating curve (AUC), with relative pooled AUCs of 1.03 (95% CI 1.00-1.07) and 1.10 (95% CI 1.07-1.13) versus physician judgement and clinical risk models alone, respectively.</p><p><strong>Conclusion: </strong>DL-based models are already used in clinical practice in certain settings for nodule management. Our results show their diagnostic performance potentially justifies wider, more routine deployment alongside experienced physician readers to help inform multidisciplinary team decision-making.</p>\",\"PeriodicalId\":18163,\"journal\":{\"name\":\"Lung\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2024-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11427562/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Lung\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s00408-024-00706-1\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/5/23 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"RESPIRATORY SYSTEM\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Lung","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00408-024-00706-1","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/5/23 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"RESPIRATORY SYSTEM","Score":null,"Total":0}
引用次数: 0

摘要

背景:人们对使用人工智能/深度学习(DL)帮助提早诊断流行性疾病的兴趣与日俱增。在这项研究中,我们试图调查经过外部验证的基于深度学习的计算机辅助诊断(CADx)模型的情况,并评估它们在预测计算机断层扫描(CT)检测到的肺结节的恶性肿瘤风险方面的诊断性能:在四个数据库中进行了电子检索(从开始到 2023 年 8 月 10 日)。只要是同行评议的实验性或观察性文章,并比较了经外部验证的基于 DL 的 CADx 模型与临床实践中广泛用于预测恶性肿瘤风险的模型的诊断性能,均符合研究条件。对纳入的研究采用双变量随机效应方法进行荟萃分析:结果:共纳入 17 项研究,包括 8553 名参与者和 9884 个结节。汇总分析表明,基于 DL 的 CADx 模型比单纯的医生判断灵敏度高 11.6%,比单纯的临床风险模型灵敏度高 14.5%。它们的集合特异性与单纯的医生判断相似[0.77(95% CI 0.68-0.84)v 0.81(95% CI 0.71-0.88)],比单纯的临床风险模型高出 7.4%。与医生判断和单独的临床风险模型相比,它们的集合接收器操作曲线下面积(AUC)更优,相对集合AUC分别为1.03(95% CI 1.00-1.07)和1.10(95% CI 1.07-1.13):结论:在某些情况下,基于 DL 的模型已被用于结节管理的临床实践中。我们的研究结果表明,它们的诊断性能有可能证明有必要更广泛、更常规地与经验丰富的医生读者一起使用,以帮助多学科团队做出知情决策。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Deep Learning Models for Predicting Malignancy Risk in CT-Detected Pulmonary Nodules: A Systematic Review and Meta-analysis.

Deep Learning Models for Predicting Malignancy Risk in CT-Detected Pulmonary Nodules: A Systematic Review and Meta-analysis.

Background: There has been growing interest in using artificial intelligence/deep learning (DL) to help diagnose prevalent diseases earlier. In this study we sought to survey the landscape of externally validated DL-based computer-aided diagnostic (CADx) models, and assess their diagnostic performance for predicting the risk of malignancy in computed tomography (CT)-detected pulmonary nodules.

Methods: An electronic search was performed in four databases (from inception to 10 August 2023). Studies were eligible if they were peer-reviewed experimental or observational articles comparing the diagnostic performance of externally validated DL-based CADx models with models widely used in clinical practice to predict the risk of malignancy. A bivariate random-effect approach for the meta-analysis on the included studies was used.

Results: Seventeen studies were included, comprising 8553 participants and 9884 nodules. Pooled analyses showed DL-based CADx models were 11.6% more sensitive than physician judgement alone, and 14.5% more than clinical risk models alone. They had a similar pooled specificity to physician judgement alone [0.77 (95% CI 0.68-0.84) v 0.81 (95% CI 0.71-0.88)], and were 7.4% more specific than clinical risk models alone. They had superior pooled areas under the receiver operating curve (AUC), with relative pooled AUCs of 1.03 (95% CI 1.00-1.07) and 1.10 (95% CI 1.07-1.13) versus physician judgement and clinical risk models alone, respectively.

Conclusion: DL-based models are already used in clinical practice in certain settings for nodule management. Our results show their diagnostic performance potentially justifies wider, more routine deployment alongside experienced physician readers to help inform multidisciplinary team decision-making.

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
Lung
Lung 医学-呼吸系统
CiteScore
9.10
自引率
10.00%
发文量
95
审稿时长
6-12 weeks
期刊介绍: Lung publishes original articles, reviews and editorials on all aspects of the healthy and diseased lungs, of the airways, and of breathing. Epidemiological, clinical, pathophysiological, biochemical, and pharmacological studies fall within the scope of the journal. Case reports, short communications and technical notes can be accepted if they are of particular interest.
×
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