High-Throughput Classification of Radiographs Using Deep Convolutional Neural Networks.
High-Throughput Classification of Radiographs Using Deep Convolutional Neural Networks.
复制标题
使用深卷积神经网络对X光片的高通量分类。
DOI：
10.1007/s10278-016-9914-9
复制
发表时间：
2017-02
影响因子：
4.4
通讯作者：
Mongan J
中科院分区：
文献类型：
--
作者：
Rajkomar A;Lingam S;Taylor AG;Blum M;Mongan J
这项研究旨在确定植根于深度学习的计算机视觉技术是否可以使用一小组射线照片来执行高保真的临床相关图像分类。对2013年1月至2015年7月在我所获得的909例患者的1,885张胸片进行了检索和匿名。源图像被手动标注为正面或侧面，并随机分为训练集、验证集和测试集。使用标准图像处理将训练和验证集扩大到150,000多张图像。然后，我们在开源的GoogLeNet的基础上，利用开源的ImageNet(非放射学)图像的各种变换，预先训练了一系列的深卷积网络。然后使用原始和增强的放射学图像对这些经过训练的网络进行微调。验证精度最高的模型被应用于我们的机构测试集和一个公开可用的集。通过使用Youden指数设置额部或侧部分类的二进制分界点来评估准确性。这项回溯性研究在启动前获得了IRB的批准。选择了一个对120万个灰度ImageNet图像进行预培训并根据增强射线照片进行微调的网络。二进制分类方法正确地对我们测试集和公开可用的图像进行了100%(95%CI 99.73-100%)的分类。分类速度很快，达到每秒38张。利用非放射学图像和扩展的X线片集建立的深度卷积神经网络对胸部X线片图像类型的高精度分类是有效的，是一种可行的、快速的高通量标注方法。
The study aimed to determine if computer vision techniques rooted in deep learning can use a small set of radiographs to perform clinically relevant image classification with high fidelity. One thousand eight hundred eighty-five chest radiographs on 909 patients obtained between January 2013 and July 2015 at our institution were retrieved and anonymized. The source images were manually annotated as frontal or lateral and randomly divided into training, validation, and test sets. Training and validation sets were augmented to over 150,000 images using standard image manipulations. We then pre-trained a series of deep convolutional networks based on the open-source GoogLeNet with various transformations of the open-source ImageNet (non-radiology) images. These trained networks were then fine-tuned using the original and augmented radiology images. The model with highest validation accuracy was applied to our institutional test set and a publicly available set. Accuracy was assessed by using the Youden Index to set a binary cutoff for frontal or lateral classification. This retrospective study was IRB approved prior to initiation. A network pre-trained on 1.2 million greyscale ImageNet images and fine-tuned on augmented radiographs was chosen. The binary classification method correctly classified 100 % (95 % CI 99.73–100 %) of both our test set and the publicly available images. Classification was rapid, at 38 images per second. A deep convolutional neural network created using non-radiological images, and an augmented set of radiographs is effective in highly accurate classification of chest radiograph view type and is a feasible, rapid method for high-throughput annotation.