Capsule Networks against Medical Imaging Data Challenges

TL;DR

This paper demonstrates that capsule networks outperform traditional ConvNets in medical imaging tasks, especially with limited data and class imbalance, making them promising for real-world medical applications.

Contribution

It provides a comparative analysis showing capsule networks require less data and are more robust to class imbalance in medical image classification.

Findings

Capsule networks perform better with limited training data.

Capsule networks are more robust to class imbalance.

Capsule networks achieve comparable or superior accuracy.

Abstract

A key component to the success of deep learning is the availability of massive amounts of training data. Building and annotating large datasets for solving medical image classification problems is today a bottleneck for many applications. Recently, capsule networks were proposed to deal with shortcomings of Convolutional Neural Networks (ConvNets). In this work, we compare the behavior of capsule networks against ConvNets under typical datasets constraints of medical image analysis, namely, small amounts of annotated data and class-imbalance. We evaluate our experiments on MNIST, Fashion-MNIST and medical (histological and retina images) publicly available datasets. Our results suggest that capsule networks can be trained with less amount of data for the same or better performance and are more robust to an imbalanced class distribution, which makes our approach very promising for the medical imaging community.