Automatic anatomical classification of esophagogastroduodenoscopy images using deep convolutional neural networks.
Automatic anatomical classification of esophagogastroduodenoscopy images using deep convolutional neural networks.
复制标题
DOI：
10.1038/s41598-018-25842-6
复制
发表时间：
2018-05-14
影响因子：
4.6
通讯作者：
Tada T
中科院分区：
文献类型：
--
作者：
Takiyama H;Ozawa T;Ishihara S;Fujishiro M;Shichijo S;Nomura S;Miura M;Tada T
卷积神经网络（cnn）的使用极大地提高了我们使用机器学习方法识别图像的能力。我们的目标是构建一个能够以适当方式识别食管胃十二指肠镜（EGD）图像解剖位置的CNN。基于GoogLeNet架构构建了一个基于cnn的诊断程序，并使用27335张EGD图像进行训练，这些图像被划分为四个主要解剖位置（喉、食管、胃和十二指肠）和胃图像的三个后续子分类（上、中、下区域）。通过绘制接收者工作特征（ROC）曲线并计算曲线下面积（aus），在17,081张EGD图像的独立验证集中评估CNN的性能。ROC曲线显示，训练后的CNN对EGD图像的解剖位置分类性能良好，喉部和食道图像的auc为1.00，胃和十二指肠图像的auc为0.99。此外，训练后的CNN可以识别胃内特定的解剖位置，上、中、下胃的auc均为0.99。总之，训练后的CNN在识别EGD图像的解剖位置方面表现出强大的性能，突出了其作为计算机辅助EGD诊断系统的未来应用潜力。
The use of convolutional neural networks (CNNs) has dramatically advanced our ability to recognize images with machine learning methods. We aimed to construct a CNN that could recognize the anatomical location of esophagogastroduodenoscopy (EGD) images in an appropriate manner. A CNN-based diagnostic program was constructed based on GoogLeNet architecture, and was trained with 27,335 EGD images that were categorized into four major anatomical locations (larynx, esophagus, stomach and duodenum) and three subsequent sub-classifications for stomach images (upper, middle, and lower regions). The performance of the CNN was evaluated in an independent validation set of 17,081 EGD images by drawing receiver operating characteristics (ROC) curves and calculating the area under the curves (AUCs). ROC curves showed high performance of the trained CNN to classify the anatomical location of EGD images with AUCs of 1.00 for larynx and esophagus images, and 0.99 for stomach and duodenum images. Furthermore, the trained CNN could recognize specific anatomical locations within the stomach, with AUCs of 0.99 for the upper, middle, and lower stomach. In conclusion, the trained CNN showed robust performance in its ability to recognize the anatomical location of EGD images, highlighting its significant potential for future application as a computer-aided EGD diagnostic system.
登录
查看更多内容
影响因子：
2.1
作者：
Kriegmair, Maximilian C.;Bergen, Tobias;Bolenz, Christian
通讯作者：
Bolenz, Christian
影响因子：
7.7
作者：
Park, Walter G.;Shaheen, Nicholas J.;Wani, Sachin
通讯作者：
Wani, Sachin
DOI：
10.1023/b:visi.0000029664.99615.94
发表时间：
2004-11-01
影响因子：
19.5
作者：
Lowe, DG
通讯作者：
Lowe, DG
影响因子：
9.3
作者：
Shibagaki, Kotaro;Amano, Yuji;Kinoshita, Yoshikazu
通讯作者：
Kinoshita, Yoshikazu
通过视频胶囊内窥镜对乳糜泻患者进行定量分析：一种深度学习方法
影响因子：
7.7
作者：
Zhou, Teng;Han, Guoqiang;Qin, Jing
通讯作者：
Qin, Jing