Hamidian Sardar, Sahiner Berkman, Petrick Nicholas, Pezeshk Aria
Department of Computer Science, George Washington University, Washington, DC.
Center for Devices and Radiological Health, U.S. Food and Drug Administration, Silver Spring, MD.
Proc SPIE Int Soc Opt Eng. 2017;10134. doi: 10.1117/12.2255795. Epub 2017 Mar 3.
Deep convolutional neural networks (CNNs) form the backbone of many state-of-the-art computer vision systems for classification and segmentation of 2D images. The same principles and architectures can be extended to three dimensions to obtain 3D CNNs that are suitable for volumetric data such as CT scans. In this work, we train a 3D CNN for automatic detection of pulmonary nodules in chest CT images using volumes of interest extracted from the LIDC dataset. We then convert the 3D CNN which has a fixed field of view to a 3D fully convolutional network (FCN) which can generate the score map for the entire volume efficiently in a single pass. Compared to the sliding window approach for applying a CNN across the entire input volume, the FCN leads to a nearly 800-fold speed-up, and thereby fast generation of output scores for a single case. This screening FCN is used to generate difficult negative examples that are used to train a new discriminant CNN. The overall system consists of the screening FCN for fast generation of candidate regions of interest, followed by the discrimination CNN.
深度卷积神经网络（CNN）构成了许多用于二维图像分类和分割的先进计算机视觉系统的核心。相同的原理和架构可以扩展到三维，以获得适用于诸如CT扫描等体数据的3D CNN。在这项工作中，我们使用从LIDC数据集中提取的感兴趣体积，训练了一个用于在胸部CT图像中自动检测肺结节的3D CNN。然后，我们将具有固定视场的3D CNN转换为3D全卷积网络（FCN），该网络可以在单次遍历中高效地为整个体积生成得分图。与在整个输入体积上应用CNN的滑动窗口方法相比，FCN的速度提高了近800倍，从而能够快速为单个病例生成输出得分。这个筛选FCN用于生成困难的负例，这些负例用于训练一个新的判别CNN。整个系统由用于快速生成感兴趣候选区域的筛选FCN和随后的判别CNN组成。
