@inproceedings{Li:2019:10.1007/978-3-030-12029-0_17,
author = {Li, L and Yang, G and Wu, F and Wong, T and Mohiaddin, R and Firmin, D and Keegan, J and Xu, L and Zhuang, X},
doi = {10.1007/978-3-030-12029-0_17},
pages = {152--160},
title = {Atrial Scar Segmentation via Potential Learning in the Graph-Cut Framework},
url = {http://dx.doi.org/10.1007/978-3-030-12029-0_17},
year = {2019}
}

Download

TY  - CPAPER
AB  - Late Gadolinium Enhancement Magnetic Resonance Imaging (LGE MRI) emerges as a routine scan for patients with atrial fibrillation (AF). However, due to the low image quality automating the quantification and analysis of the atrial scars is challenging. In this study, we proposed a fully automated method based on the graph-cut framework, where the potential of the graph is learned on a surface mesh of the left atrium (LA), using an equidistant projection and a deep neural network (DNN). For validation, we employed 100 datasets with manual delineation. The results showed that the performance of the proposed method was improved and converged with respect to the increased size of training patches, which provide important features of the structural and texture information learned by the DNN. The segmentation could be further improved when the contribution from the t-link and n-link is balanced, thanks to the inter-relationship learned by the DNN for the graph-cut algorithm. Compared with the existing methods which mostly acquired an initialization from manual delineation of the LA or LA wall, our method is fully automated and has demonstrated great potentials in tackling this task. The accuracy of quantifying the LA scars using the proposed method was 0.822, and the Dice score was 0.566. The results are promising and the method can be useful in diagnosis and prognosis of AF.
AU  - Li,L
AU  - Yang,G
AU  - Wu,F
AU  - Wong,T
AU  - Mohiaddin,R
AU  - Firmin,D
AU  - Keegan,J
AU  - Xu,L
AU  - Zhuang,X
DO  - 10.1007/978-3-030-12029-0_17
EP  - 160
PY  - 2019///
SN  - 0302-9743
SP  - 152
TI  - Atrial Scar Segmentation via Potential Learning in the Graph-Cut Framework
UR  - http://dx.doi.org/10.1007/978-3-030-12029-0_17
ER  - 

Download