Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks
Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks
复制标题
DOI：
10.1109/tmi.2016.2536809
复制
发表时间：
2016-05-01
影响因子：
10.6
通讯作者：
van Ginneken, Bram
中科院分区：
文献类型：
--
作者：
Setio, Arnaud Arindra Adiyoso;Ciompi, Francesco;van Ginneken, Bram
我们提出了一种新的计算机辅助检测（CAD）系统的肺结节使用多视图卷积网络（ConvNets），判别特征是自动学习的训练数据。该网络馈与结核候选人通过结合三个候选人探测器专门设计的固体，亚固体，和大结节。对于每个候选者，从不同取向的平面提取一组2-D补丁。所提出的架构包括多个2-D ConvNets流，使用专用融合方法将其输出组合以获得最终分类。应用数据增广和丢弃以避免过拟合。在公开的LIDC-IDRI数据集的888次扫描中，我们的方法在每次扫描1次和4次假阳性时分别达到了85.4%和90.1%的高检测灵敏度。对来自ANODE 09挑战和DLCST的独立数据集进行额外评价。我们表明，所提出的多视图ConvNets非常适合用于减少CAD系统的误报。
We propose a novel Computer-Aided Detection (CAD) system for pulmonary nodules using multi-view convolutional networks (ConvNets), for which discriminative features are automatically learnt from the training data. The network is fed with nodule candidates obtained by combining three candidate detectors specifically designed for solid, subsolid, and large nodules. For each candidate, a set of 2-D patches from differently oriented planes is extracted. The proposed architecture comprises multiple streams of 2-D ConvNets, for which the outputs are combined using a dedicated fusion method to get the final classification. Data augmentation and dropout are applied to avoid overfitting. On 888 scans of the publicly available LIDC-IDRI dataset, our method reaches high detection sensitivities of 85.4% and 90.1% at 1 and 4 false positives per scan, respectively. An additional evaluation on independent datasets from the ANODE09 challenge and DLCST is performed. We showed that the proposed multi-view ConvNets is highly suited to be used for false positive reduction of a CAD system.