Imperial College London
Portrait Picture

DrTimothyDawes

Faculty of Medicine, National Heart & Lung Institute

Honorary Clinical Lecturer
 
 
 
//

Contact

 

+44 (0)20 3313 3298tim.dawes Website

 
 
//

Location

 

MRC London Institute of Medical Sciences, 111 ISDRobert Steiner MR unitHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Duan:2018:10.1007/978-3-030-04747-4_24,
author = {Duan, J and Schlemper, J and Bai, W and Dawes, TJW and Bello, G and Biffi, C and Doumou, G and De, Marvao A and O’Regan, DP and Rueckert, D},
doi = {10.1007/978-3-030-04747-4_24},
pages = {258--267},
publisher = {Springer Verlag},
title = {Combining deep learning and shape priors for bi-ventricular segmentation of volumetric cardiac magnetic resonance images},
url = {http://dx.doi.org/10.1007/978-3-030-04747-4_24},
year = {2018}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - In this paper, we combine a network-based method with image registration to develop a shape-based bi-ventricular segmentation tool for short-axis cardiac magnetic resonance (CMR) volumetric images. The method first employs a fully convolutional network (FCN) to learn the segmentation task from manually labelled ground truth CMR volumes. However, due to the presence of image artefacts in the training dataset, the resulting FCN segmentation results are often imperfect. As such, we propose a second step to refine the FCN segmentation. This step involves performing a non-rigid registration with multiple high-resolution bi-ventricular atlases, allowing the explicit shape priors to be inferred. We validate the proposed approach on 1831 healthy subjects and 200 subjects with pulmonary hypertension. Numerical experiments on the two datasets demonstrate that our approach is capable of producing accurate, high-resolution and anatomically smooth bi-ventricular models, despite the artefacts in the input CMR volumes.
AU  - Duan,J
AU  - Schlemper,J
AU  - Bai,W
AU  - Dawes,TJW
AU  - Bello,G
AU  - Biffi,C
AU  - Doumou,G
AU  - De,Marvao A
AU  - O’Regan,DP
AU  - Rueckert,D
DO  - 10.1007/978-3-030-04747-4_24
EP  - 267
PB  - Springer Verlag
PY  - 2018///
SN  - 0302-9743
SP  - 258
TI  - Combining deep learning and shape priors for bi-ventricular segmentation of volumetric cardiac magnetic resonance images
UR  - http://dx.doi.org/10.1007/978-3-030-04747-4_24
UR  - http://hdl.handle.net/10044/1/77499
ER  -
Download