Department of Gastroenterology and Hepatology, Amsterdam Gastroenterology, Endocrinology and Metabolism, University of Amsterdam, Amsterdam, the Netherlands.
Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.
United European Gastroenterol J. 2023 May;11(4):324-336. doi: 10.1002/ueg2.12363. Epub 2023 Apr 24.
INTRODUCTION: Endoscopic detection of early neoplasia in Barrett's esophagus is difficult. Computer Aided Detection (CADe) systems may assist in neoplasia detection. The aim of this study was to report the first steps in the development of a CADe system for Barrett's neoplasia and to evaluate its performance when compared with endoscopists. METHODS: This CADe system was developed by a consortium, consisting of the Amsterdam University Medical Center, Eindhoven University of Technology, and 15 international hospitals. After pretraining, the system was trained and validated using 1.713 neoplastic (564 patients) and 2.707 non-dysplastic Barrett's esophagus (NDBE; 665 patients) images. Neoplastic lesions were delineated by 14 experts. The performance of the CADe system was tested on three independent test sets. Test set 1 (50 neoplastic and 150 NDBE images) contained subtle neoplastic lesions representing challenging cases and was benchmarked by 52 general endoscopists. Test set 2 (50 neoplastic and 50 NDBE images) contained a heterogeneous case-mix of neoplastic lesions, representing distribution in clinical practice. Test set 3 (50 neoplastic and 150 NDBE images) contained prospectively collected imagery. The main outcome was correct classification of the images in terms of sensitivity. RESULTS: The sensitivity of the CADe system on test set 1 was 84%. For general endoscopists, sensitivity was 63%, corresponding to a neoplasia miss-rate of one-third of neoplastic lesions and a potential relative increase in neoplasia detection of 33% for CADe-assisted detection. The sensitivity of the CADe system on test sets 2 and 3 was 100% and 88%, respectively. The specificity of the CADe system varied for the three test sets between 64% and 66%. CONCLUSION: This study describes the first steps towards the establishment of an unprecedented data infrastructure for using machine learning to improve the endoscopic detection of Barrett's neoplasia. The CADe system detected neoplasia reliably and outperformed a large group of endoscopists in terms of sensitivity.
简介：在 Barrett 食管中检测早期肿瘤较为困难。计算机辅助检测（CADe）系统可能有助于肿瘤检测。本研究旨在报告开发 Barrett 肿瘤 CADe 系统的初步步骤，并评估其与内镜医生相比的性能。
方法：该 CADe 系统由阿姆斯特丹大学医学中心、埃因霍温科技大学以及 15 家国际医院组成的联盟开发。在预训练后，该系统使用 1713 例肿瘤性（564 例患者）和 2707 例非异型性 Barrett 食管（NDBE；665 例患者）图像进行训练和验证。肿瘤病变由 14 名专家划定。CADe 系统的性能在三个独立的测试集上进行了测试。测试集 1（50 例肿瘤性和 150 例 NDBE 图像）包含代表挑战性病例的微妙肿瘤性病变，并由 52 名普通内镜医生进行了基准测试。测试集 2（50 例肿瘤性和 50 例 NDBE 图像）包含了肿瘤病变的异质病例组合，代表了临床实践中的分布情况。测试集 3（50 例肿瘤性和 150 例 NDBE 图像）包含了前瞻性采集的图像。主要结果是根据敏感性正确分类图像。
结果：CADe 系统在测试集 1 上的敏感性为 84%。对于普通内镜医生，敏感性为 63%，这意味着三分之一的肿瘤性病变被漏诊，CADe 辅助检测的肿瘤性检测相对增加了 33%。CADe 系统在测试集 2 和 3 上的敏感性分别为 100%和 88%。CADe 系统的特异性在三个测试集中分别在 64%至 66%之间。
结论：本研究描述了朝着建立一个前所未有的使用机器学习来改善 Barrett 食管肿瘤检测的数据基础设施的第一步。CADe 系统可靠地检测到了肿瘤，并在敏感性方面优于一大群内镜医生。
Lancet Digit Health. 2023-12
United European Gastroenterol J. 2019-3-6
Gastrointest Endosc. 2017-3-16
Endoscopy. 2016-4-21
Gastrointest Endosc. 2020-2
Auris Nasus Larynx. 2025-5-21
Clin Endosc. 2025-7
United European Gastroenterol J. 2025-7
Diagnostics (Basel). 2023-9-5
Int J Comput Assist Radiol Surg. 2019-1-22
Zotero 插件