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

Cardiac segmentation from late gadolinium enhancement MRI is an importanttask in clinics to identify and evaluate the infarction of myocardium. Theautomatic segmentation is however still challenging, due to the heterogeneousintensity distributions and indistinct boundaries in the images. In this paper,we propose a new method, based on deep neural networks (DNN), for fullyautomatic segmentation. The proposed network, referred to as SRSCN, comprises ashape reconstruction neural network (SRNN) and a spatial constraint network(SCN). SRNN aims to maintain a realistic shape of the resulting segmentation.It can be pre-trained by a set of label images, and then be embedded into aunified loss function as a regularization term. Hence, no manually designedfeature is needed. Furthermore, SCN incorporates the spatial information of the2D slices. It is formulated and trained with the segmentation network via themulti-task learning strategy. We evaluated the proposed method using 45patients and compared with two state-of-the-art regularization schemes, i.e.,the anatomically constraint neural network and the adversarial neural network.The results show that the proposed SRSCN outperformed the conventional schemes,and obtained a Dice score of 0.758(std=0.227) for myocardial segmentation,which compares with 0.757(std=0.083) from the inter-observer variations.

Cardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priors