Effect of Input Size on the Classification of Lung Nodules Using Convolutional Neural Networks

TL;DR

This paper investigates how input volume size affects the performance of CNN-based lung nodule classification in CT scans, demonstrating that larger volumes improve accuracy and that 3D CNNs outperform 2D CNNs.

Contribution

It introduces a CNN framework that analyzes CT lung scans with varying volume sizes, highlighting the importance of input size and fusion methods for improved detection accuracy.

Findings

Larger input volumes enhance classification performance.

3D CNNs outperform 2D CNNs in lung nodule detection.

The framework achieved a sensitivity of 0.831 at 1 false positive per scan.

Abstract

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.