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/

Zendy Plus

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

Zendy Tools

Zendy Open

Accurate and reliable brain tumor segmentation is a critical component incancer diagnosis, treatment planning, and treatment outcome evaluation. Buildupon successful deep learning techniques, a novel brain tumor segmentationmethod is developed by integrating fully convolutional neural networks (FCNNs)and Conditional Random Fields (CRFs) in a unified framework to obtainsegmentation results with appearance and spatial consistency. We train a deeplearning based segmentation model using 2D image patches and image slices infollowing steps: 1) training FCNNs using image patches; 2) training CRFs asRecurrent Neural Networks (CRF-RNN) using image slices with parameters of FCNNsfixed; and 3) fine-tuning the FCNNs and the CRF-RNN using image slices.Particularly, we train 3 segmentation models using 2D image patches and slicesobtained in axial, coronal and sagittal views respectively, and combine them tosegment brain tumors using a voting based fusion strategy. Our method couldsegment brain images slice-by-slice, much faster than those based on imagepatches. We have evaluated our method based on imaging data provided by theMultimodal Brain Tumor Image Segmentation Challenge (BRATS) 2013, BRATS 2015and BRATS 2016. The experimental results have demonstrated that our methodcould build a segmentation model with Flair, T1c, and T2 scans and achievecompetitive performance as those built with Flair, T1, T1c, and T2 scans.

A deep learning model integrating FCNNs and CRFs for brain tumor segmentation