Division of Imaging, Diagnostics, and Software Reliability (DIDSR), OSEL, CDRH, FDA, Silver Spring, MD, 20993, USA.
Multimedia Laboratory, University of Louisville, Louisville, KY, 40292, USA.
Med Phys. 2020 Jun;47(5):2150-2160. doi: 10.1002/mp.14076. Epub 2020 Mar 18.
Multiview two-dimensional (2D) convolutional neural networks (CNNs) and three-dimensional (3D) CNNs have been successfully used for analyzing volumetric data in many state-of-the-art medical imaging applications. We propose an alternative modular framework that analyzes volumetric data with an approach that is analogous to radiologists' interpretation, and apply the framework to reduce false positives that are generated in computer-aided detection (CADe) systems for pulmonary nodules in thoracic computed tomography (CT) scans.
In our approach, a deep network consisting of 2D CNNs first processes slices individually. The features extracted in this stage are then passed to a recurrent neural network (RNN), thereby modeling consecutive slices as a sequence of temporal data and capturing the contextual information across all three dimensions in the volume of interest. Outputs of the RNN layer are weighed before the final fully connected layer, enabling the network to scale the importance of different slices within a volume of interest in an end-to-end training framework.
We validated the proposed architecture on the false positive reduction track of the lung nodule analysis (LUNA) challenge for pulmonary nodule detection in chest CT scans, and obtained competitive results compared to 3D CNNs. Our results show that the proposed approach can encode the 3D information in volumetric data effectively by achieving a sensitivity >0.8 with just 1/8 false positives per scan.
Our experimental results demonstrate the effectiveness of temporal analysis of volumetric images for the application of false positive reduction in chest CT scans and show that state-of-the-art 2D architectures from the literature can be directly applied to analyzing volumetric medical data. As newer and better 2D architectures are being developed at a much faster rate compared to 3D architectures, our approach makes it easy to obtain state-of-the-art performance on volumetric data using new 2D architectures.
多视图二维（2D）卷积神经网络（CNN）和三维（3D）CNN 已成功应用于许多最先进的医学成像应用中的体积数据分析。我们提出了一种替代的模块化框架，该框架采用类似于放射科医生解释的方法来分析体积数据，并将该框架应用于减少计算机辅助检测（CADe）系统在胸部 CT 扫描中检测肺结节时产生的假阳性。
在我们的方法中，一个由 2D CNN 组成的深度网络首先单独处理切片。在此阶段提取的特征然后传递给递归神经网络（RNN），从而将连续切片建模为时间数据序列，并捕获感兴趣体积中所有三个维度的上下文信息。在最终的全连接层之前对 RNN 层的输出进行加权，从而使网络能够在端到端训练框架中调整感兴趣体积内不同切片的重要性。
我们在胸部 CT 扫描中肺结节检测的肺结节分析（LUNA）挑战的假阳性减少跟踪中验证了所提出的架构，并与 3D CNN 相比获得了有竞争力的结果。我们的结果表明，通过仅每扫描 1/8 的假阳性即可实现>0.8 的灵敏度，该方法可以有效地对体积数据中的 3D 信息进行编码。
我们的实验结果证明了对体积图像进行时间分析在减少胸部 CT 扫描中的假阳性方面的有效性，并表明文献中的最新二维架构可以直接应用于分析体积医学数据。由于与 3D 架构相比，更新和更好的 2D 架构的开发速度要快得多，因此我们的方法使使用新的 2D 架构在体积数据上获得最新性能变得容易。
