Capsule Networks against Medical Imaging Data Challenges

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 imbal-anced class distribution, which makes our approach very promising for the medical imaging community.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-02049352
Contributor : Diana Mateus <>
Submitted on : Tuesday, February 26, 2019 - 12:40:38 PM
Last modification on : Tuesday, March 26, 2019 - 9:25:22 AM

File

1807.07559.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02049352, version 1

Collections

Citation

Amelia Jiménez-Sánchez, Shadi Albarqouni, Diana Mateus. Capsule Networks against Medical Imaging Data Challenges. MICCAI Workshop LABELS (Large-Scale Annotation of Biomedical Data and Expert Label Synthesis), Sep 2018, Granada, Spain. ⟨hal-02049352⟩

Share

Metrics

Record views

12

Files downloads

25