Capsule Networks against Medical Imaging Data Challenges

Amelia Jiménez Sánchez, Shadi Albarqouni, Diana Mateus

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review


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.
TitelLABELS 2018, CVII 2018, STENT 2018: Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis
ForlagSpringer Nature
Publikationsdato17 okt. 2018
ISBN (Trykt)978-3-030-01363-9
ISBN (Elektronisk)978-3-030-01364-6
StatusUdgivet - 17 okt. 2018
Udgivet eksterntJa


Dyk ned i forskningsemnerne om 'Capsule Networks against Medical Imaging Data Challenges'. Sammen danner de et unikt fingeraftryk.