Department of Gastroenterology and Hepatology, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, The Netherlands.
Department of Electrical Engineering, Video Coding & Architectures group, Eindhoven University of Technology, Eindhoven, The Netherlands.
Gastroenterology. 2020 Mar;158(4):915-929.e4. doi: 10.1053/j.gastro.2019.11.030. Epub 2019 Nov 22.
BACKGROUND & AIMS: We aimed to develop and validate a deep-learning computer-aided detection (CAD) system, suitable for use in real time in clinical practice, to improve endoscopic detection of early neoplasia in patients with Barrett's esophagus (BE).
We developed a hybrid ResNet-UNet model CAD system using 5 independent endoscopy data sets. We performed pretraining using 494,364 labeled endoscopic images collected from all intestinal segments. Then, we used 1704 unique esophageal high-resolution images of rigorously confirmed early-stage neoplasia in BE and nondysplastic BE, derived from 669 patients. System performance was assessed by using data sets 4 and 5. Data set 5 was also scored by 53 general endoscopists with a wide range of experience from 4 countries to benchmark CAD system performance. Coupled with histopathology findings, scoring of images that contained early-stage neoplasia in data sets 2-5 were delineated in detail for neoplasm position and extent by multiple experts whose evaluations served as the ground truth for segmentation.
The CAD system classified images as containing neoplasms or nondysplastic BE with 89% accuracy, 90% sensitivity, and 88% specificity (data set 4, 80 patients and images). In data set 5 (80 patients and images) values for the CAD system vs those of the general endoscopists were 88% vs 73% accuracy, 93% vs 72% sensitivity, and 83% vs 74% specificity. The CAD system achieved higher accuracy than any of the individual 53 nonexpert endoscopists, with comparable delineation performance. CAD delineations of the area of neoplasm overlapped with those from the BE experts in all detected neoplasia in data sets 4 and 5. The CAD system identified the optimal site for biopsy of detected neoplasia in 97% and 92% of cases (data sets 4 and 5, respectively).
We developed, validated, and benchmarked a deep-learning computer-aided system for primary detection of neoplasia in patients with BE. The system detected neoplasia with high accuracy and near-perfect delineation performance. The Netherlands National Trials Registry, Number: NTR7072.
我们旨在开发和验证一种深度学习计算机辅助检测（CAD）系统，使其适用于临床实践中的实时使用，以提高对 Barrett 食管（BE）患者早期肿瘤的内镜检测。
我们使用 5 个独立的内镜数据集开发了一种混合 ResNet-UNet 模型 CAD 系统。我们使用来自所有肠段的 494364 个标记内镜图像进行预训练。然后，我们使用 669 名患者的 1704 个严格确认的 BE 和非异型增生 BE 早期肿瘤的独特食管高分辨率图像。使用数据集 4 和 5 评估系统性能。数据集 5 还由来自 4 个国家的具有广泛经验的 53 名普通内镜医生进行评分，以衡量 CAD 系统的性能。结合组织病理学结果，详细划定数据集 2-5 中包含早期肿瘤的图像的肿瘤位置和范围，由多位专家进行评估，这些评估结果作为分割的真实情况。
CAD 系统以 89%的准确率、90%的敏感性和 88%的特异性（数据集 4，80 名患者和图像）将图像分类为含有肿瘤或非异型增生 BE。在数据集 5（80 名患者和图像）中，CAD 系统与普通内镜医生的数值分别为 88%和 73%的准确率、93%和 72%的敏感性以及 83%和 74%的特异性。CAD 系统的准确率高于任何一位非专家内镜医生，且具有可比的分割性能。在数据集 4 和 5 中，CAD 系统对所有检测到的肿瘤的肿瘤区域的描绘与 BE 专家的描绘重叠。CAD 系统在 97%和 92%的情况下（分别为数据集 4 和 5）确定了检测到的肿瘤的最佳活检部位。
我们开发、验证和基准测试了一种用于 BE 患者早期肿瘤初筛的深度学习计算机辅助系统。该系统以高精度和近乎完美的描绘性能检测肿瘤。荷兰国家试验注册处，编号：NTR7072。
