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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep convolutional neural networks have achieved remarkable progress on avariety of medical image computing tasks. A common problem when applyingsupervised deep learning methods to medical images is the lack of labeled data,which is very expensive and time-consuming to be collected. In this paper, wepresent a novel semi-supervised method for medical image segmentation, wherethe network is optimized by the weighted combination of a common supervisedloss for labeled inputs only and a regularization loss for both labeled andunlabeled data. To utilize the unlabeled data, our method encourages theconsistent predictions of the network-in-training for the same input underdifferent regularizations. Aiming for the semi-supervised segmentation problem,we enhance the effect of regularization for pixel-level predictions byintroducing a transformation, including rotation and flipping, consistentscheme in our self-ensembling model. With the aim of semi-supervisedsegmentation tasks, we introduce a transformation consistent strategy in ourself-ensembling model to enhance the regularization effect for pixel-levelpredictions. We have extensively validated the proposed semi-supervised methodon three typical yet challenging medical image segmentation tasks: (i) skinlesion segmentation from dermoscopy images on International Skin ImagingCollaboration (ISIC) 2017 dataset, (ii) optic disc segmentation from fundusimages on Retinal Fundus Glaucoma Challenge (REFUGE) dataset, and (iii) liversegmentation from volumetric CT scans on Liver Tumor Segmentation Challenge(LiTS) dataset. Compared to the state-of-the-arts, our proposed method showssuperior segmentation performance on challenging 2D/3D medical images,demonstrating the effectiveness of our semi-supervised method for medical imagesegmentation.

Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation