Effect of Input Size on the Classification of Lung Nodules Using Convolutional Neural Networks
This work addresses the burden on radiologists in analyzing CT scans for lung cancer screening, but it is incremental as it builds on existing CAD systems and focuses on optimizing input parameters.
The study tackled the problem of reducing false positives in lung nodule classification from CT scans by analyzing the effect of input volume size and fusion methods using convolutional neural networks, achieving a sensitivity of 0.831 at 1 false positive per scan on the LUNA16 dataset.
Recent studies have shown that lung cancer screening using annual low-dose computed tomography (CT) reduces lung cancer mortality by 20% compared to traditional chest radiography. Therefore, CT lung screening has started to be used widely all across the world. However, analyzing these images is a serious burden for radiologists. The number of slices in a CT scan can be up to 600. Therefore, computer-aided-detection (CAD) systems are very important for faster and more accurate assessment of the data. In this study, we proposed a framework that analyzes CT lung screenings using convolutional neural networks (CNNs) to reduce false positives. We trained our model with different volume sizes and showed that volume size plays a critical role in the performance of the system. We also used different fusions in order to show their power and effect on the overall accuracy. 3D CNNs were preferred over 2D CNNs because 2D convolutional operations applied to 3D data could result in information loss. The proposed framework has been tested on the dataset provided by the LUNA16 Challenge and resulted in a sensitivity of 0.831 at 1 false positive per scan.