English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we introduce a simple, yet powerful pipeline for medical imagesegmentation that combines Fully Convolutional Networks (FCNs) with FullyConvolutional Residual Networks (FC-ResNets). We propose and examine a designthat takes particular advantage of recent advances in the understanding of bothConvolutional Neural Networks as well as ResNets. Our approach focuses upon theimportance of a trainable pre-processing when using FC-ResNets and we show thata low-capacity FCN model can serve as a pre-processor to normalize medicalinput data. In our image segmentation pipeline, we use FCNs to obtainnormalized images, which are then iteratively refined by means of a FC-ResNetto generate a segmentation prediction. As in other fully convolutionalapproaches, our pipeline can be used off-the-shelf on different imagemodalities. We show that using this pipeline, we exhibit state-of-the-artperformance on the challenging Electron Microscopy benchmark, when compared toother 2D methods. We improve segmentation results on CT images of liverlesions, when contrasting with standard FCN methods. Moreover, when applyingour 2D pipeline on a challenging 3D MRI prostate segmentation challenge wereach results that are competitive even when compared to 3D methods. Theobtained results illustrate the strong potential and versatility of thepipeline by achieving highly accurate results on multi-modality images fromdifferent anatomical regions and organs.

Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation