Multisource Transfer Learning With Convolutional Neural Networks for Lung Pattern Analysis
Multisource Transfer Learning With Convolutional Neural Networks for Lung Pattern Analysis
复制标题
DOI：
10.1109/jbhi.2016.2636929
复制
发表时间：
2017-01-01
影响因子：
7.7
通讯作者：
Mougiakakou, Stavroula
中科院分区：
文献类型：
--
作者：
Christodoulidis, Stergios;Anthimopoulos, Marios;Mougiakakou, Stavroula
间质性肺疾病的早期诊断对其治疗至关重要，但即使是经验丰富的医生也发现这很困难，因为它们的临床表现相似。为了辅助诊断，已经开发了计算机辅助诊断系统。这些通常依赖于固定比例的分类器来扫描 CT 图像、识别肺部纹理模式并生成病理图。在之前的研究中，我们提出了一种使用深度卷积神经网络（CNN）对肺组织模式进行分类的方法，并具有针对特定问题设计的架构。在本研究中，我们提出了一种改进的方法，通过从通用纹理分类的相似领域转移知识来训练所提出的网络。六个公开可用的纹理数据库用于使用所提出的架构来预训练网络，然后根据肺组织数据进行微调。由此产生的 CNN 被组合成一个整体，它们的融合知识被压缩回具有原始架构的网络。所提出的方法使所提出的 CNN 性能绝对提高了约 2%。结果证明了迁移学习在医学图像分析领域的潜力，表明了问题的纹理本质，并表明用于训练网络的方法与设计其架构一样重要。
Early diagnosis of interstitial lung diseases is crucial for their treatment, but even experienced physicians find it difficult, as their clinical manifestations are similar. In order to assist with the diagnosis, computer-aided diagnosis systems have been developed. These commonly rely on a fixed scale classifier that scans CT images, recognizes textural lung patterns, and generates a map of pathologies. In a previous study, we proposed a method for classifying lung tissue patterns using a deep convolutional neural network (CNN), with an architecture designed for the specific problem. In this study, we present an improved method for training the proposed network by transferring knowledge from the similar domain of general texture classification. Six publicly available texture databases are used to pretrain networks with the proposed architecture, which are then fine-tuned on the lung tissue data. The resulting CNNs are combined in an ensemble and their fused knowledge is compressed back to a network with the original architecture. The proposed approach resulted in an absolute increase of about 2% in the performance of the proposed CNN. The results demonstrate the potential of transfer learning in the field of medical image analysis, indicate the textural nature of the problem and show that the method used for training a network can be as important as designing its architecture.