Imperial College London
Portrait Picture

ProfessorDavidFirmin

Faculty of Medicine, National Heart & Lung Institute

Emeritus Professor of Biomedical Imaging
 
 
 
//

Contact

 

+44 (0)20 7351 8801d.firmin

 
 
//

Location

 

Cardiovascular MR UnitRoyal Brompton Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Chen:2018:10.1007/978-3-030-00934-2_51,
author = {Chen, J and Yang, G and Gao, Z and Ni, H and Angelini, E and Mohiaddin, R and Wong, T and Zhang, Y and Du, X and Zhang, H and Keegan, J and Firmin, D},
doi = {10.1007/978-3-030-00934-2_51},
pages = {455--463},
publisher = {Springer},
title = {Multiview two-task recursive attention model for left atrium and atrial scars segmentation},
url = {http://dx.doi.org/10.1007/978-3-030-00934-2_51},
year = {2018}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Late Gadolinium Enhanced Cardiac MRI (LGE-CMRI) for detecting atrial scars in atrial fibrillation (AF) patients has recently emerged as a promising technique to stratify patients, guide ablation therapy and predict treatment success. Visualisation and quantification of scar tissues require a segmentation of both the left atrium (LA) and the high intensity scar regions from LGE-CMRI images. These two segmentation tasks are challenging due to the cancelling of healthy tissue signal, low signal-to-noise ratio and often limited image quality in these patients. Most approaches require manual supervision and/or a second bright-blood MRI acquisition for anatomical segmentation. Segmenting both the LA anatomy and the scar tissues automatically from a single LGE-CMRI acquisition is highly in demand. In this study, we proposed a novel fully automated multiview two-task (MVTT) recursive attention model working directly on LGE-CMRI images that combines a sequential learning and a dilated residual learning to segment the LA (including attached pulmonary veins) and delineate the atrial scars simultaneously via an innovative attention model. Compared to other state-of-the-art methods, the proposed MVTT achieves compelling improvement, enabling to generate a patient-specific anatomical and atrial scar assessment model.
AU  - Chen,J
AU  - Yang,G
AU  - Gao,Z
AU  - Ni,H
AU  - Angelini,E
AU  - Mohiaddin,R
AU  - Wong,T
AU  - Zhang,Y
AU  - Du,X
AU  - Zhang,H
AU  - Keegan,J
AU  - Firmin,D
DO  - 10.1007/978-3-030-00934-2_51
EP  - 463
PB  - Springer
PY  - 2018///
SN  - 0302-9743
SP  - 455
TI  - Multiview two-task recursive attention model for left atrium and atrial scars segmentation
UR  - http://dx.doi.org/10.1007/978-3-030-00934-2_51
UR  - https://link.springer.com/chapter/10.1007%2F978-3-030-00934-2_51
UR  - http://hdl.handle.net/10044/1/71711
ER  -
Download