• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

基于深度学习的无线胶囊内镜对息肉识别的诊断准确性:一项荟萃分析。

Diagnostic Accuracy of Wireless Capsule Endoscopy in Polyp Recognition Using Deep Learning: A Meta-Analysis.

作者信息

Mi Junjie, Han Xiaofang, Wang Rong, Ma Ruijun, Zhao Danyu

机构信息

Digestive Endoscopy Center, Shanxi Provincial People's Hospital, Taiyuan, China.

Reproductive Medicine, Shanxi Provincial People's Hospital, Taiyuan, China.

出版信息

Int J Clin Pract. 2022 Mar 19;2022:9338139. doi: 10.1155/2022/9338139. eCollection 2022.

DOI:10.1155/2022/9338139
PMID:35685533
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9159236/
Abstract

AIM

As the completed studies have small sample sizes and different algorithms, a meta-analysis was conducted to assess the accuracy of WCE in identifying polyps using deep learning.

METHOD

Two independent reviewers searched PubMed, Embase, the Web of Science, and the Cochrane Library for potentially eligible studies published up to December 8, 2021, which were analysed on a per-image basis. STATA RevMan and Meta-DiSc were used to conduct this meta-analysis. A random effects model was used, and a subgroup and regression analysis was performed to explore sources of heterogeneity.

RESULTS

Eight studies published between 2017 and 2021 included 819 patients, and 18,414 frames were eventually included in the meta-analysis. The summary estimates for the WCE in identifying polyps by deep learning were sensitivity 0.97 (95% confidence interval (CI), 0.95-0.98); specificity 0.97 (95% CI, 0.94-0.98); positive likelihood ratio 27.19 (95% CI, 15.32-50.42); negative likelihood ratio 0.03 (95% CI 0.02-0.05); diagnostic odds ratio 873.69 (95% CI, 387.34-1970.74); and the area under the sROC curve 0.99.

CONCLUSION

WCE uses deep learning to identify polyps with high accuracy, but multicentre prospective randomized controlled studies are needed in the future.

摘要

目的

由于已完成的研究样本量较小且算法不同,因此进行了一项荟萃分析,以评估深度学习在识别息肉方面的 WCE 准确性。

方法

两位独立审查员搜索了 PubMed、Embase、Web of Science 和 Cochrane Library,以查找截至 2021 年 12 月 8 日发表的潜在合格研究,这些研究基于图像进行分析。使用 STATA RevMan 和 Meta-DiSc 进行这项荟萃分析。使用随机效应模型,并进行亚组和回归分析以探索异质性的来源。

结果

2017 年至 2021 年期间发表的八项研究纳入了 819 名患者,最终有 18414 个框架纳入荟萃分析。深度学习识别息肉的 WCE 的汇总估计值为:敏感性 0.97(95%置信区间(CI),0.95-0.98);特异性 0.97(95% CI,0.94-0.98);阳性似然比 27.19(95% CI,15.32-50.42);阴性似然比 0.03(95% CI 0.02-0.05);诊断比值比 873.69(95% CI,387.34-1970.74);和 sROC 曲线下面积 0.99。

结论

WCE 使用深度学习识别息肉的准确率高,但未来需要多中心前瞻性随机对照研究。

相似文献

1
Diagnostic Accuracy of Wireless Capsule Endoscopy in Polyp Recognition Using Deep Learning: A Meta-Analysis.基于深度学习的无线胶囊内镜对息肉识别的诊断准确性:一项荟萃分析。
2
Deep learning for wireless capsule endoscopy: a systematic review and meta-analysis.深度学习在无线胶囊内窥镜中的应用:系统评价和荟萃分析。
Gastrointest Endosc. 2020 Oct;92(4):831-839.e8. doi: 10.1016/j.gie.2020.04.039. Epub 2020 Apr 22.
3
Diagnostic accuracy of computed tomography colonography in patients at high risk for colorectal cancer: a meta-analysis.计算机断层结肠成像在结直肠癌高危患者中的诊断准确性:一项荟萃分析。
Colorectal Dis. 2020 Nov;22(11):1528-1537. doi: 10.1111/codi.15060. Epub 2020 Apr 27.
4
Deep Convolutional Neural Network for Ulcer Recognition in Wireless Capsule Endoscopy: Experimental Feasibility and Optimization.无线胶囊内窥镜中溃疡识别的深度卷积神经网络:实验可行性与优化。
Comput Math Methods Med. 2019 Sep 18;2019:7546215. doi: 10.1155/2019/7546215. eCollection 2019.
5
Convolution neural network for the diagnosis of wireless capsule endoscopy: a systematic review and meta-analysis.卷积神经网络在无线胶囊内镜诊断中的应用:系统评价和荟萃分析。
Surg Endosc. 2022 Jan;36(1):16-31. doi: 10.1007/s00464-021-08689-3. Epub 2021 Aug 23.
6
Use of Wireless Capsule Endoscopy for the Diagnosis and Grading of Esophageal Varices in Patients With Portal Hypertension: A Systematic Review and Meta-Analysis.无线胶囊内镜在门静脉高压患者食管静脉曲张诊断及分级中的应用:一项系统评价与Meta分析
J Clin Gastroenterol. 2017 Feb;51(2):174-182. doi: 10.1097/MCG.0000000000000589.
7
Deep learning for detection of age-related macular degeneration: A systematic review and meta-analysis of diagnostic test accuracy studies.深度学习在年龄相关性黄斑变性检测中的应用:诊断性试验准确性研究的系统评价和荟萃分析。
PLoS One. 2023 Apr 6;18(4):e0284060. doi: 10.1371/journal.pone.0284060. eCollection 2023.
8
Deep learning for polyp recognition in wireless capsule endoscopy images.用于无线胶囊内窥镜图像中息肉识别的深度学习
Med Phys. 2017 Apr;44(4):1379-1389. doi: 10.1002/mp.12147.
9
Deep learning for registration of region of interest in consecutive wireless capsule endoscopy frames.基于深度学习的无线胶囊内窥镜连续帧中感兴趣区域的配准。
Comput Methods Programs Biomed. 2021 Sep;208:106189. doi: 10.1016/j.cmpb.2021.106189. Epub 2021 May 25.
10
A computer-aided diagnostic system for intestinal polyps identified by wireless capsule endoscopy.一种用于通过无线胶囊内镜识别肠道息肉的计算机辅助诊断系统。
Rom J Morphol Embryol. 2016;57(3):979-984.

引用本文的文献

1
Diagnostic performance of AI-assisted endoscopy diagnosis of digestive system tumors: an umbrella review.人工智能辅助内镜诊断消化系统肿瘤的诊断性能:一项伞状综述。
Front Oncol. 2025 Apr 3;15:1519144. doi: 10.3389/fonc.2025.1519144. eCollection 2025.
2
Clinical and demographic features of patients undergoing video-capsule endoscopy management: A descriptive study.接受视频胶囊内镜检查管理的患者的临床和人口统计学特征:一项描述性研究。
World J Gastrointest Endosc. 2024 Jul 16;16(7):424-431. doi: 10.4253/wjge.v16.i7.424.

本文引用的文献

1
Application of artificial intelligence in COVID-19 medical area: a systematic review.人工智能在COVID-19医学领域的应用:一项系统综述。
J Thorac Dis. 2021 Dec;13(12):7034-7053. doi: 10.21037/jtd-21-747.
2
Artificial intelligence and colon capsule endoscopy: development of an automated diagnostic system of protruding lesions in colon capsule endoscopy.人工智能与结肠胶囊内镜:结肠胶囊内镜中突出性病变自动诊断系统的研发。
Tech Coloproctol. 2021 Nov;25(11):1243-1248. doi: 10.1007/s10151-021-02517-5. Epub 2021 Sep 9.
3
Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis.深度学习在医学成像中的诊断准确性:一项系统评价与荟萃分析。
NPJ Digit Med. 2021 Apr 7;4(1):65. doi: 10.1038/s41746-021-00438-z.
4
Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries.《全球癌症统计数据 2020:全球 185 个国家和地区 36 种癌症的发病率和死亡率估计》。
CA Cancer J Clin. 2021 May;71(3):209-249. doi: 10.3322/caac.21660. Epub 2021 Feb 4.
5
Multicentre, prospective, randomised study comparing the diagnostic yield of colon capsule endoscopy versus CT colonography in a screening population (the TOPAZ study).多中心、前瞻性、随机对照研究比较了在筛查人群中胶囊结肠镜与 CT 结肠成像的诊断效果(TOPAZ 研究)。
Gut. 2021 Nov;70(11):2115-2122. doi: 10.1136/gutjnl-2020-322578. Epub 2020 Dec 18.
6
The use of artificial intelligence and robotics in regional anaesthesia.人工智能和机器人技术在区域麻醉中的应用。
Anaesthesia. 2021 Jan;76 Suppl 1:171-181. doi: 10.1111/anae.15274.
7
A Low Power and Real-Time Architecture for Hough Transform Processing Integration in a Full HD-Wireless Capsule Endoscopy.一种用于全高清无线胶囊内窥镜中霍夫变换处理集成的低功耗实时架构。
IEEE Trans Biomed Circuits Syst. 2020 Aug;14(4):646-657. doi: 10.1109/TBCAS.2020.3008458. Epub 2020 Jul 10.
8
Colon capsule endoscopy: an innovative method for detecting colorectal pathology during the COVID-19 pandemic?结肠胶囊内镜:COVID-19 大流行期间检测结直肠病理的创新方法?
Colorectal Dis. 2020 Jun;22(6):621-624. doi: 10.1111/codi.15134. Epub 2020 Jun 2.
9
Deep learning for wireless capsule endoscopy: a systematic review and meta-analysis.深度学习在无线胶囊内窥镜中的应用:系统评价和荟萃分析。
Gastrointest Endosc. 2020 Oct;92(4):831-839.e8. doi: 10.1016/j.gie.2020.04.039. Epub 2020 Apr 22.
10
Urine Sediment Recognition Method Based on Multi-View Deep Residual Learning in Microscopic Image.基于微观图像多视图深度残差学习的尿沉渣识别方法。
J Med Syst. 2019 Oct 23;43(11):325. doi: 10.1007/s10916-019-1457-4.