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

The most recent fast and accurate image segmentation methods are built uponfully convolutional deep neural networks. In this paper, we propose new deeplearning strategies for DenseNets to improve segmenting images with subtledifferences in intensity values and features. We aim to segment brain tissue oninfant brain MRI at about 6 months of age where white matter and gray matter ofthe developing brain show similar T1 and T2 relaxation times, thus appear tohave similar intensity values on both T1- and T2-weighted MRI scans. Braintissue segmentation at this age is, therefore, very challenging. To this end,we propose an exclusive multi-label training strategy to segment the mutuallyexclusive brain tissues with similarity loss functions that automaticallybalance the training based on class prevalence. Using our proposed trainingstrategy based on similarity loss functions and patch prediction fusion wedecrease the number of parameters in the network, reduce the complexity of thetraining process focusing the attention on less number of tasks, whilemitigating the effects of data imbalance between labels and inaccuracies nearpatch borders. By taking advantage of these strategies we were able to performfast image segmentation (90 seconds per 3D volume), using a network with lessparameters than many state-of-the-art networks, overcoming issues such as3Dvs2D training and large vs small patch size selection, while achieving thetop performance in segmenting brain tissue among all methods tested in firstand second round submissions of the isointense infant brain MRI segmentation(iSeg) challenge according to the official challenge test results. Our proposedstrategy improves the training process through balanced training and byreducing its complexity while providing a trained model that works for any sizeinput image and is fast and more accurate than many state-of-the-art methods.

Exclusive Independent Probability Estimation using Deep 3D Fully Convolutional DenseNets: Application to IsoIntense Infant Brain MRI Segmentation