Fast CapsNet for Lung Cancer Screening

TL;DR

This paper introduces a faster capsule network architecture tailored for lung nodule classification in CT scans, demonstrating improved performance with limited training data and proposing a more efficient decoding method.

Contribution

It presents a novel, faster CapsNet with a dynamic routing mechanism and an improved convolutional decoder for better lung nodule classification.

Findings

CapsNets outperform CNNs with small training datasets.

The proposed dynamic routing speeds up CapsNet by 3 times.

The convolutional decoder reduces reconstruction error and improves accuracy.

Abstract

Lung cancer is the leading cause of cancer-related deaths in the past several years. A major challenge in lung cancer screening is the detection of lung nodules from computed tomography (CT) scans. State-of-the-art approaches in automated lung nodule classification use deep convolutional neural networks (CNNs). However, these networks require a large number of training samples to generalize well. This paper investigates the use of capsule networks (CapsNets) as an alternative to CNNs. We show that CapsNets significantly outperforms CNNs when the number of training samples is small. To increase the computational efficiency, our paper proposes a consistent dynamic routing mechanism that results in $3\times$ speedup of CapsNet. Finally, we show that the original image reconstruction method of CapNets performs poorly on lung nodule data. We propose an efficient alternative, called convolutional decoder, that yields lower reconstruction error and higher classification accuracy.