Gastroenterologist-Level Identification of Small-Bowel Diseases and Normal Variants by Capsule Endoscopy Using a Deep-Learning Model
Gastroenterologist-Level Identification of Small-Bowel Diseases and Normal Variants by Capsule Endoscopy Using a Deep-Learning Model
复制标题
使用深度学习模型通过胶囊内窥镜对小肠疾病和正常变异进行胃肠病学家级别的识别
DOI：
10.1053/j.gastro.2019.06.025
复制
发表时间：
2019-10-01
期刊：
影响因子：
29.4
通讯作者：
Hou, Xiaohua
中科院分区：
文献类型：
--
作者：
Ding, Zhen;Shi, Huiying;Hou, Xiaohua
背景与目的：胶囊内镜彻底改变了小肠的研究。然而，这种技术产生的视频长达8-10小时，因此分析对于胃肠病学家来说是耗时的。深度卷积神经网络（CNN）可以识别大量图像中的特定图像。我们旨在开发一种基于CNN的算法，以帮助评价小肠胶囊式内窥镜（SB-CE）图像。方法：我们从2016年7月至2018年7月在77家医疗中心接受SB-CE的6970例患者中收集了113，426，569张图像。使用来自1970名患者的158，235张SB-CE图像，训练基于CNN的辅助阅读模型，以区分异常图像和正常图像。图像分类为正常、炎症、溃疡、息肉、淋巴管扩张、出血、血管疾病、突出病变、淋巴滤泡增生、憩室、寄生虫和其他。该模型在5000例患者中进一步验证（没有患者与训练集中的1970例患者重叠）;由20名胃肠病学家通过常规分析和基于CNN的辅助分析对相同患者进行评价。如果常规分析和CNN模型之间的图像分类一致，则不进行进一步的评价。如果传统分析和CNN模型之间存在分歧，胃肠病学家将重新评估图像以确认或拒绝CNN分类。结果：在来自验证集的SB-CE图像中，在最终共识评价后，在3280例患者中识别出4206例异常。基于CNN的辅助模型在每例患者分析中以99.88%的灵敏度（95% CI，99.67-99.96）识别异常，在每例病变分析中以99.90%的灵敏度（95% CI，99.74-99.97）识别异常。胃肠病学家的常规阅读在按患者分析和按病变分析中分别识别出74.57%（95% CI，73.05-76.03）和76.89%（95% CI，75.58-78.15）的异常。每例患者的平均阅读时间为96.6 +/- 22.53分钟（常规阅读）和5.9 +/- 2.23分钟（基于CNN的辅助阅读）（P < .001）。结论：我们验证了基于CNN的算法识别SB-CE图像异常的能力。基于CNN的辅助模型识别出的异常具有更高的灵敏度水平，并且比胃肠病学家的常规分析显著缩短了阅读时间。该算法为胃肠病学家更有效、更准确地分析SB-CE图像提供了重要工具。
BACKGROUND & AIMS: Capsule endoscopy has revolutionized investigation of the small bowel. However, this technique produces a video that is 8-10 hours long, so analysis is time consuming for gastroenterologists. Deep convolutional neural networks (CNNs) can recognize specific images among a large variety. We aimed to develop a CNN-based algorithm to assist in the evaluation of small bowel capsule endoscopy (SB-CE) images. METHODS: We collected 113,426,569 images from 6970 patients who had SB-CE at 77 medical centers from July 2016 through July 2018. A CNN-based auxiliary reading model was trained to differentiate abnormal from normal images using 158,235 SB-CE images from 1970 patients. Images were categorized as normal, inflammation, ulcer, polyps, lymphangiectasia, bleeding, vascular disease, protruding lesion, lymphatic follicular hyperplasia, diverticulum, parasite, and other. The model was further validated in 5000 patients (no patient was overlap with the 1970 patients in the training set); the same patients were evaluated by conventional analysis and CNN-based auxiliary analysis by 20 gastroenterologists. If there was agreement in image categorization between the conventional analysis and CNN model, no further evaluation was performed. If there was disagreement between the conventional analysis and CNN model, the gastroenterologists re-evaluated the image to confirm or reject the CNN categorization. RESULTS: In the SB-CE images from the validation set, 4206 abnormalities in 3280 patients were identified after final consensus evaluation. The CNN-based auxiliary model identified abnormalities with 99.88% sensitivity in the per-patient analysis (95% CI, 99.67-99.96) and 99.90% sensitivity in the per-lesion analysis (95% CI, 99.74-99.97). Conventional reading by the gastroenterologists identified abnormalities with 74.57% sensitivity (95% CI, 73.05-76.03) in the per-patient analysis and 76.89% in the per-lesion analysis (95% CI, 75.58-78.15). The mean reading time per patient was 96.6 +/- 22.53 minutes by conventional reading and 5.9 +/- 2.23 minutes by CNN-based auxiliary reading (P < .001). CONCLUSIONS: We validated the ability of a CNN-based algorithm to identify abnormalities in SB-CE images. The CNN-based auxiliary model identified abnormalities with higher levels of sensitivity and significantly shorter reading times than conventional analysis by gastroenterologists. This algorithm provides an important tool to help gastroenterologists analyze SB-CE images more efficiently and more accurately.