Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning.
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning.
复制标题
用于计算机辅助检测的深度卷积神经网络：卷积神经网络架构、数据集特征与迁移学习
DOI：
10.1109/tmi.2016.2528162
复制
发表时间：
2016-05
影响因子：
10.6
通讯作者：
Summers RM
中科院分区：
文献类型：
--
作者：
Shin HC;Roth HR;Gao M;Lu L;Xu Z;Nogues I;Yao J;Mollura D;Summers RM
图像识别已经取得了显着的进展，主要是由于大规模注释数据集和深度卷积神经网络（CNN）的可用性。CNN能够从足够的训练数据中学习数据驱动的、高度代表性的、分层的图像特征。然而，在医学成像领域获得像ImageNet一样全面注释的数据集仍然是一个挑战。目前有三种主要技术成功地将CNN应用于医学图像分类：从头开始训练CNN，使用现成的预训练CNN特征，以及通过监督微调进行无监督CNN预训练。另一种有效的方法是迁移学习，即，微调从自然图像数据集到医学图像任务预训练的CNN模型。在本文中，我们利用了三个重要的，但以前研究不足的因素，将深度卷积神经网络用于计算机辅助检测问题。我们首先探索和评估不同的CNN架构。所研究的模型包含5千到1.6亿个参数，并且层数不同。然后，我们评估数据集规模和空间图像上下文对性能的影响。最后，我们研究了什么时候以及为什么从预先训练的ImageNet（通过微调）进行迁移学习是有用的。我们研究了两个特定的计算机辅助检测（CADe）问题，即胸腹淋巴结（LN）检测和间质性肺病（ILD）分类。我们在纵隔LN检测方面实现了最先进的性能，并报告了预测ILD类别轴向CT切片的第一个五重交叉验证分类结果。我们广泛的经验评估，CNN模型分析和有价值的见解可以扩展到其他医学成像任务的高性能CAD系统的设计。
Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.