面向早期Barrett肿瘤初步检测的强大且紧凑的深度学习系统：多中心回顾性数据集上基于图像的训练的初始结果。
Towards a robust and compact deep learning system for primary detection of early Barrett's neoplasia: Initial image-based results of training on a multi-center retrospectively collected data set.
发表日期：2023 Apr 24
作者：
Kiki N Fockens, Jelmer B Jukema, Tim Boers, Martijn R Jong, Joost A van der Putten, Roos E Pouw, Bas L A M Weusten, Lorenza Alvarez Herrero, Martin H M G Houben, Wouter B Nagengast, Jessie Westerhof, Alaa Alkhalaf, Rosalie Mallant, Krish Ragunath, Stefan Seewald, Peter Elbe, Maximilien Barret, Jacobo Ortiz Fernández-Sordo, Oliver Pech, Torsten Beyna, Fons van der Sommen, Peter H de With, A Jeroen de Groof, Jacques J Bergman
来源：
United European Gastroenterology Journal
摘要：
在 Barrett 食道病变早期肿瘤的内窥镜检测方面存在困难。计算机辅助检测 (CADe) 系统可以协助发现肿瘤。本研究旨在报告开发 Barrett 肿瘤 CADe 系统的第一步，并评估其与内窥镜医师相比的表现。该 CADe 系统是由阿姆斯特丹大学医学中心、埃因霍温科技大学和 15 家国际医院组成的联合体开发的。系统经过预训练后，使用 1,713 张肿瘤 (564 名患者) 和 2,707 张非异形性 Barrett 食道病变 (NDBE; 665 名患者) 图像进行了训练和验证。14 名专家勾勒了肿瘤病变。CADe 系统的表现在三个独立的测试集上进行了测试。测试集 1 (50 张肿瘤和 150 张 NDBE 图像) 包含代表具有挑战性病例的微妙的肿瘤病变，并由 52 名常规内窥镜医师进行基准测试。测试集 2 (50 张肿瘤和 50 张 NDBE 图像) 包含不同类型的混合病例，代表了临床实践中的分布。测试集 3 (50 张肿瘤和 150 张 NDBE 图像) 包含预期收集的图像。主要结果是以灵敏度为衡量标准对图像进行正确分类。CADe 系统在测试集 1 上的灵敏度为 84%。对于一般内窥镜医师，灵敏度为 63%，相当于肿瘤病变漏诊率为三分之一，并且 CADe 辅助检测可能相对提高肿瘤病变检测率 33%。CADe 系统在测试集 2 和 3 上的灵敏度分别为 100% 和 88%。CADe 系统的特异性在三个测试集之间变化，在 64% 和 66% 之间。本研究描述了建立无前例的数据基础设施以使用机器学习来改善 Barrett 肿瘤内窥镜检测的第一步。CADe 系统可靠地检测肿瘤病变，并在灵敏度方面优于大组内窥镜医师。©2023 Wiley Periodicals LLC 为欧洲胃肠病学联合期刊代表欧洲胃肠病学会发布。
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.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.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%.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.© 2023 The Authors. United European Gastroenterology Journal published by Wiley Periodicals LLC on behalf of United European Gastroenterology.