Classification of Lung Nodule Malignancy Risk on Computed Tomography Images Using Convolutional Neural Network: A Comparison Between 2D and 3D Strategies

Abstract

Computed tomography (CT) is the preferred method for non-invasive lung cancer screening. Early detection of potentially malignant lung nodules will greatly improve patient outcome, where an effective computer-aided diagnosis (CAD) system may play an important role. Two-dimensional convolutional neural network (CNN) based CAD methods have been proposed and well-studied to extract hierarchical and discriminative features for classifying lung nodules. It is often questioned if the transition to 3D will be a key to major step forward in performance. In this paper, we propose a novel 3D CNN on the 1018-patient Lung Image Database Consortium collection (LIDC-IDRI). To the best of our knowledge, this is the first time to directly compare three different strategies: slice-level 2D CNN, nodule-level 2D CNN and nodule-level 3D CNN. Using comparable network architectures, we achieved nodule malignancy risk classification accuracies of $86.7\%$, $87.3\%$ and $87.4\%$ against the personal opinion of four radiologists, respectively. In the experiments, our results and analyses demonstrates that the nodule-level 2D CNN can better capture the z-direction features of lung nodule than a slice-level 2D approach, whereas nodule-level 3D CNN can further integrate nodule-level features as well as context features from all three directions in a 3D patch in a limited extent, resulting in a slightly better performance than the other two strategies.