Fast CapsNet for Lung Cancer Screening
Published in
International Conference on Medical Image Compu...(2018)External Links:
TL
TL;DR
It is shown that CapsNets significantly outperforms CNNs when the number of training samples is small, and an efficient alternative, called convolutional decoder, is proposed that yields lower reconstruction error and higher classification 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.
References8 items
1
Dynamic Routing Between Capsules
2
Deep Residual Learning for Image Recognition
3
ImageNet classification with deep convolutional neural networks
4
Reduced lung-cancer mortality with low-dose computed tomographic screening.
5