• 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

KID项目：一个用于研究目的的基于互联网的胶囊内镜数字视频图谱。

KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes.

作者信息

Koulaouzidis Anastasios, Iakovidis Dimitris K, Yung Diana E, Rondonotti Emanuele, Kopylov Uri, Plevris John N, Toth Ervin, Eliakim Abraham, Wurm Johansson Gabrielle, Marlicz Wojciech, Mavrogenis Georgios, Nemeth Artur, Thorlacius Henrik, Tontini Gian Eugenio

机构信息

Centre for Liver and Digestive Disorders, The Royal Infirmary of Edinburgh, Edinburgh, UK.

University of Thessaly, Department of Computer Science and Biomedical Informatics, Volos, Thessaly, Greece.

出版信息

Endosc Int Open. 2017 Jun;5(6):E477-E483. doi: 10.1055/s-0043-105488. Epub 2017 May 31.

DOI:10.1055/s-0043-105488
PMID:28580415
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC5452962/
Abstract

BACKGROUND AND AIMS

Capsule endoscopy (CE) has revolutionized small-bowel (SB) investigation. Computational methods can enhance diagnostic yield (DY); however, incorporating machine learning algorithms (MLAs) into CE reading is difficult as large amounts of image annotations are required for training. Current databases lack graphic annotations of pathologies and cannot be used. A novel database, KID, aims to provide a reference for research and development of medical decision support systems (MDSS) for CE.

METHODS

Open-source software was used for the KID database. Clinicians contribute anonymized, annotated CE images and videos. Graphic annotations are supported by an open-access annotation tool (Ratsnake). We detail an experiment based on the KID database, examining differences in SB lesion measurement between human readers and a MLA. The Jaccard Index (JI) was used to evaluate similarity between annotations by the MLA and human readers.

RESULTS

The MLA performed best in measuring lymphangiectasias with a JI of 81 ± 6 %. The other lesion types were: angioectasias (JI 64 ± 11 %), aphthae (JI 64 ± 8 %), chylous cysts (JI 70 ± 14 %), polypoid lesions (JI 75 ± 21 %), and ulcers (JI 56 ± 9 %).

CONCLUSION

MLA can perform as well as human readers in the measurement of SB angioectasias in white light (WL). Automated lesion measurement is therefore feasible. KID is currently the only open-source CE database developed specifically to aid development of MDSS. Our experiment demonstrates this potential.

摘要

背景与目的

胶囊内镜检查（CE）彻底改变了小肠（SB）检查方式。计算方法可提高诊断率（DY）；然而，将机器学习算法（MLA）纳入CE阅片存在困难，因为训练需要大量图像标注。当前数据库缺乏病变的图形标注，无法使用。一个新的数据库KID旨在为CE医学决策支持系统（MDSS）的研发提供参考。

方法

KID数据库使用开源软件。临床医生提供匿名的、带标注的CE图像和视频。图形标注由一个开放获取的标注工具（Ratsnake）支持。我们详细介绍了一项基于KID数据库的实验，研究人类阅片者和MLA在SB病变测量上的差异。使用Jaccard指数（JI）评估MLA和人类阅片者标注之间的相似度。

结果

MLA在测量淋巴管扩张方面表现最佳，JI为81±6%。其他病变类型为：血管扩张（JI 64±11%）、阿弗他溃疡（JI 64±8%）、乳糜囊肿（JI 70±14%）、息肉样病变（JI 75±21%）和溃疡（JI 56±9%）。

结论

在白光（WL）下测量SB血管扩张时，MLA的表现与人类阅片者相当。因此，自动病变测量是可行的。KID是目前唯一专门为辅助MDSS开发而建立的开源CE数据库。我们的实验证明了这一潜力。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/8f5a2fcb43b1/10-1055-s-0043-105488-i701ei7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/361a4f85bf21/10-1055-s-0043-105488-i701ei1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/3ae3de6796b7/10-1055-s-0043-105488-i701ei2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/bd0f81ee78f1/10-1055-s-0043-105488-i701ei3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/72e90a246400/10-1055-s-0043-105488-i701ei4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/fe61e9ecbaf7/10-1055-s-0043-105488-i701ei5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/5ced621aefbf/10-1055-s-0043-105488-i701ei6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/8f5a2fcb43b1/10-1055-s-0043-105488-i701ei7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/361a4f85bf21/10-1055-s-0043-105488-i701ei1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/3ae3de6796b7/10-1055-s-0043-105488-i701ei2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/bd0f81ee78f1/10-1055-s-0043-105488-i701ei3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/72e90a246400/10-1055-s-0043-105488-i701ei4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/fe61e9ecbaf7/10-1055-s-0043-105488-i701ei5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/5ced621aefbf/10-1055-s-0043-105488-i701ei6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5306/5452962/8f5a2fcb43b1/10-1055-s-0043-105488-i701ei7.jpg

相似文献

1
KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes.KID项目：一个用于研究目的的基于互联网的胶囊内镜数字视频图谱。
Endosc Int Open. 2017 Jun;5(6):E477-E483. doi: 10.1055/s-0043-105488. Epub 2017 May 31.
2
CAD-CAP: a 25,000-image database serving the development of artificial intelligence for capsule endoscopy.CAD-CAP：一个拥有25000张图像的数据库，用于支持胶囊内镜人工智能的开发。
Endosc Int Open. 2020 Mar;8(3):E415-E420. doi: 10.1055/a-1035-9088. Epub 2020 Feb 21.
3
Gastroenterologist-Level Identification of Small-Bowel Diseases and Normal Variants by Capsule Endoscopy Using a Deep-Learning Model.胶囊内镜使用深度学习模型对小肠疾病和正常变异进行胃肠病学家级别的识别。
Gastroenterology. 2019 Oct;157(4):1044-1054.e5. doi: 10.1053/j.gastro.2019.06.025. Epub 2019 Jun 25.
4
A neural network algorithm for detection of GI angiectasia during small-bowel capsule endoscopy.一种用于小肠胶囊内镜检查中胃肠道血管扩张检测的神经网络算法。
Gastrointest Endosc. 2019 Jan;89(1):189-194. doi: 10.1016/j.gie.2018.06.036. Epub 2018 Jul 11.
5
Small bowel capsule endoscopy examination and open access database with artificial intelligence: The SEE-artificial intelligence project.小肠胶囊内镜检查与带人工智能的开放获取数据库：SEE人工智能项目。
DEN Open. 2023 Jun 22;4(1):e258. doi: 10.1002/deo2.258. eCollection 2024 Apr.
6
A new artificial intelligence system for both stomach and small-bowel capsule endoscopy.一种用于胃部和小肠胶囊内镜的新型人工智能系统。
Gastrointest Endosc. 2024 Nov;100(5):878.e1-878.e14. doi: 10.1016/j.gie.2024.06.004. Epub 2024 Jun 6.
7
Diagnostic yield of capsule endoscopy versus magnetic resonance enterography and small bowel contrast ultrasound in the evaluation of small bowel Crohn's disease: Systematic review and meta-analysis.胶囊内镜与磁共振肠造影和小肠对比超声在小肠克罗恩病评估中的诊断率：系统评价和荟萃分析。
Dig Liver Dis. 2017 Aug;49(8):854-863. doi: 10.1016/j.dld.2017.04.013. Epub 2017 Apr 27.
8
Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach.使用实例分割方法进行 WCE 视频中的多病理学检测和病变定位。
Artif Intell Med. 2021 Sep;119:102141. doi: 10.1016/j.artmed.2021.102141. Epub 2021 Aug 10.
9
Clinical utility of capsule endoscopy with flexible spectral imaging color enhancement for diagnosis of small bowel lesions.采用灵活光谱成像颜色增强技术的胶囊内镜在小肠病变诊断中的临床应用价值
Endosc Int Open. 2014 Jun;2(2):E80-7. doi: 10.1055/s-0034-1365526. Epub 2014 May 7.
10
Virtual chromoendoscopy can be a useful software tool in capsule endoscopy.虚拟染色内镜检查在胶囊内镜中是一种有用的软件工具。
Rev Esp Enferm Dig. 2012 May;104(5):231-6. doi: 10.4321/s1130-01082012000500002.

引用本文的文献

1
Utilizing Deep Convolutional Neural Networks and Hybrid Classification for Gastrointestinal Disease Diagnosis from Capsule Endoscopy Images.利用深度卷积神经网络和混合分类方法从胶囊内镜图像诊断胃肠疾病
J Biomed Phys Eng. 2025 Aug 1;15(4):369-384. doi: 10.31661/jbpe.v0i0.2301-1590. eCollection 2025 Aug.
2
Advancing Colorectal Cancer Diagnostics from Barium Enema to AI-Assisted Colonoscopy.将结直肠癌诊断从钡剂灌肠推进到人工智能辅助结肠镜检查。
Diagnostics (Basel). 2025 Apr 11;15(8):974. doi: 10.3390/diagnostics15080974.
3
Application of artificial intelligence in gastrointestinal endoscopy in Vietnam: a narrative review.

本文引用的文献

1
Computer-aided detection of early neoplastic lesions in Barrett's esophagus.计算机辅助检测 Barrett 食管早期肿瘤病变。
Endoscopy. 2016 Jul;48(7):617-24. doi: 10.1055/s-0042-105284. Epub 2016 Apr 21.
2
Supervised Evaluation of Image Segmentation and Object Proposal Techniques.监督式图像分割与目标建议技术评估。
IEEE Trans Pattern Anal Mach Intell. 2016 Jul;38(7):1465-78. doi: 10.1109/TPAMI.2015.2481406. Epub 2015 Sep 23.
3
Software for enhanced video capsule endoscopy: challenges for essential progress.用于增强视频胶囊内镜的软件：取得实质性进展的挑战。
人工智能在越南胃肠内镜检查中的应用：一项叙述性综述。
Ther Adv Gastrointest Endosc. 2024 Dec 23;17:26317745241306562. doi: 10.1177/26317745241306562. eCollection 2024 Jan-Dec.
4
Gastrointestinal tract disease detection via deep learning based structural and statistical features optimized hexa-classification model.基于深度学习的结构和统计特征优化六分类模型的胃肠道疾病检测。
Technol Health Care. 2024;32(6):4453-4473. doi: 10.3233/THC-240603.
5
Polypoid Lesion Segmentation Using YOLO-V8 Network in Wireless Video Capsule Endoscopy Images.基于YOLO-V8网络的无线视频胶囊内镜图像中息肉样病变分割
Diagnostics (Basel). 2024 Feb 22;14(5):474. doi: 10.3390/diagnostics14050474.
6
Wireless capsule endoscopy multiclass classification using three-dimensional deep convolutional neural network model.基于三维深度卷积神经网络模型的无线胶囊内镜多分类。
Biomed Eng Online. 2023 Dec 15;22(1):124. doi: 10.1186/s12938-023-01186-9.
7
Public Imaging Datasets of Gastrointestinal Endoscopy for Artificial Intelligence: a Review.用于人工智能的胃肠道内镜公共成像数据集：综述。
J Digit Imaging. 2023 Dec;36(6):2578-2601. doi: 10.1007/s10278-023-00844-7. Epub 2023 Sep 21.
8
E pluribus unum interpretable convolutional neural networks.可解释的卷积神经网络。
Sci Rep. 2023 Jul 14;13(1):11421. doi: 10.1038/s41598-023-38459-1.
9
Small bowel capsule endoscopy examination and open access database with artificial intelligence: The SEE-artificial intelligence project.小肠胶囊内镜检查与带人工智能的开放获取数据库：SEE人工智能项目。
DEN Open. 2023 Jun 22;4(1):e258. doi: 10.1002/deo2.258. eCollection 2024 Apr.
10
A multi-centre polyp detection and segmentation dataset for generalisability assessment.用于泛化能力评估的多中心息肉检测和分割数据集。
Sci Data. 2023 Feb 6;10(1):75. doi: 10.1038/s41597-023-01981-y.
Nat Rev Gastroenterol Hepatol. 2015 Mar;12(3):172-86. doi: 10.1038/nrgastro.2015.13. Epub 2015 Feb 17.
4
Automatic lesion detection in capsule endoscopy based on color saliency: closer to an essential adjunct for reviewing software.基于颜色显著性的胶囊内镜自动病变检测：更接近用于回顾软件的重要辅助手段。
Gastrointest Endosc. 2014 Nov;80(5):877-83. doi: 10.1016/j.gie.2014.06.026. Epub 2014 Aug 1.
5
Ratsnake: a versatile image annotation tool with application to computer-aided diagnosis.锦蛇：一种适用于计算机辅助诊断的多功能图像标注工具。
ScientificWorldJournal. 2014 Jan 27;2014:286856. doi: 10.1155/2014/286856. eCollection 2014.
6
Capsule endoscopy as a panenteric diagnostic tool.胶囊内镜作为一种全肠道诊断工具。
Br J Surg. 2014 Feb;101(3):148-9. doi: 10.1002/bjs.9321. Epub 2013 Nov 19.
7
Small-bowel capsule endoscopy: a ten-point contemporary review.小肠胶囊内镜：十点当代综述。
World J Gastroenterol. 2013 Jun 28;19(24):3726-46. doi: 10.3748/wjg.v19.i24.3726.
8
Detection of lesions during capsule endoscopy: physician performance is disappointing.胶囊内镜检查中病变的检测：医师表现令人失望。
Am J Gastroenterol. 2012 Apr;107(4):554-60. doi: 10.1038/ajg.2011.461. Epub 2012 Jan 10.
9
Localizing region-based active contours.基于区域的主动轮廓定位
IEEE Trans Image Process. 2008 Nov;17(11):2029-39. doi: 10.1109/TIP.2008.2004611.
10
The informatics opportunities at the intersection of patient safety and clinical informatics.患者安全与临床信息学交叉领域的信息学机遇。
J Am Med Inform Assoc. 2008 Jul-Aug;15(4):397-407. doi: 10.1197/jamia.M2735. Epub 2008 Apr 24.