BayesCap: A Bayesian Approach to Brain Tumor Classification Using Capsule Networks

Convolutional neural networks (CNNs), which have been the state-of-the-art in many image-related applications, are prone to losing important spatial information between image instances. Capsule networks (CapsNets), on the other hand, are capable of leveraging such information through their routing b...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2020, Vol.27, p.2024-2028
Main Authors: Afshar, Parnian, Mohammadi, Arash, Plataniotis, Konstantinos N.
Format: Article
Language:English
Subjects:
Artificial neural networks
Bayes methods
Bayesian analysis
Bayesian Capsule Networks
Brain
Brain cancer
Brain modeling
Brain Tumor Classification
Classification
Deep learning
Machine learning
Measurement uncertainty
Medical imaging
Predictive models
Radiomics
Spatial data
Tumors
Uncertainty
Uncertainty Measure
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Convolutional neural networks (CNNs), which have been the state-of-the-art in many image-related applications, are prone to losing important spatial information between image instances. Capsule networks (CapsNets), on the other hand, are capable of leveraging such information through their routing by agreement process, making them powerful architectures for small datasets, such as medical imaging ones. Within the domain of medical imaging problems, brain tumor classification is of paramount importance, due to the deadly nature of this cancer and the consequences of the tumor misclassification. In our recent works, we showed potentials of developing CapsNet architecture for the task of brain tumor type classification. Similar to other deep learning models, however, CapsNets do not capture prediction uncertainty (coming from the uncertainty in the model weights, which is significantly important in keeping the human experts in the loop, by returning the uncertain samples. In this paper, we propose a Bayesian CapsNet framework, referred to as the \text{BayesCap}, that can provide not only the mean predictions, but also entropy as a measure of prediction uncertainty. Results show that filtering out the uncertain predictions can improve the accuracy, confirming that returning the uncertain predictions is an appropriate strategy for improving interpretability of the network.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2020.3034858