dc.contributor.author |
Xiong, Zhaohan |
|
dc.contributor.author |
Fedorov, Vadim V |
|
dc.contributor.author |
Fu, Xiaohang |
|
dc.contributor.author |
Cheng, Elizabeth |
|
dc.contributor.author |
Macleod, Rob |
|
dc.contributor.author |
Zhao, Jichao |
|
dc.coverage.spatial |
United States |
|
dc.date.accessioned |
2021-05-11T22:40:04Z |
|
dc.date.available |
2021-05-11T22:40:04Z |
|
dc.date.issued |
2019-2 |
|
dc.identifier.citation |
IEEE transactions on medical imaging 38(2):515-524 Feb 2019 |
|
dc.identifier.issn |
0278-0062 |
|
dc.identifier.uri |
https://hdl.handle.net/2292/55079 |
|
dc.description.abstract |
Atrial fibrillation (AF) is the most prevalent form of cardiac arrhythmia. Current treatments for AF remain suboptimal due to a lack of understanding of the underlying atrial structures that directly sustain AF. Existing approaches for analyzing atrial structures in 3-D, especially from late gadolinium-enhanced (LGE) magnetic resonance imaging, rely heavily on manual segmentation methods that are extremely labor-intensive and prone to errors. As a result, a robust and automated method for analyzing atrial structures in 3-D is of high interest. We have, therefore, developed AtriaNet, a 16-layer convolutional neural network (CNN), on 154 3-D LGE-MRIs with a spatial resolution of 0.625 mm ×0.625 mm ×1.25 mm from patients with AF, to automatically segment the left atrial (LA) epicardium and endocardium. AtriaNet consists of a multi-scaled, dual-pathway architecture that captures both the local atrial tissue geometry and the global positional information of LA using 13 successive convolutions and three further convolutions for merging. By utilizing computationally efficient batch prediction, AtriaNet was able to successfully process each 3-D LGE-MRI within 1 min. Furthermore, benchmarking experiments have shown that AtriaNet has outperformed the state-of-the-art CNNs, with a DICE score of 0.940 and 0.942 for the LA epicardium and endocardium, respectively, and an inter-patient variance of <0.001. The estimated LA diameter and volume computed from the automatic segmentations were accurate to within 1.59 mm and 4.01 cm3 of the ground truths. Our proposed CNN was tested on the largest known data set for LA segmentation, and to the best of our knowledge, it is the most robust approach that has ever been developed for segmenting LGE-MRIs. The increased accuracy of atrial reconstruction and analysis could potentially improve the understanding and treatment of AF. |
|
dc.format.medium |
Print |
|
dc.language |
eng |
|
dc.publisher |
Institute of Electrical and Electronics Engineers (IEEE) |
|
dc.relation.ispartofseries |
IEEE transactions on medical imaging |
|
dc.rights |
Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. |
|
dc.rights |
© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
|
dc.rights.uri |
https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm |
|
dc.rights.uri |
https://www.ieee.org/publications/rights/author-posting-policy.html |
|
dc.subject |
Heart Atria |
|
dc.subject |
Humans |
|
dc.subject |
Atrial Fibrillation |
|
dc.subject |
Gadolinium |
|
dc.subject |
Imaging, Three-Dimensional |
|
dc.subject |
Magnetic Resonance Imaging |
|
dc.subject |
Algorithms |
|
dc.subject |
Neural Networks, Computer |
|
dc.subject |
Algorithms |
|
dc.subject |
Atrial Fibrillation |
|
dc.subject |
Gadolinium |
|
dc.subject |
Heart Atria |
|
dc.subject |
Humans |
|
dc.subject |
Imaging, Three-Dimensional |
|
dc.subject |
Magnetic Resonance Imaging |
|
dc.subject |
Neural Networks, Computer |
|
dc.subject |
Science & Technology |
|
dc.subject |
Technology |
|
dc.subject |
Life Sciences & Biomedicine |
|
dc.subject |
Computer Science, Interdisciplinary Applications |
|
dc.subject |
Engineering, Biomedical |
|
dc.subject |
Engineering, Electrical & Electronic |
|
dc.subject |
Imaging Science & Photographic Technology |
|
dc.subject |
Radiology, Nuclear Medicine & Medical Imaging |
|
dc.subject |
Computer Science |
|
dc.subject |
Engineering |
|
dc.subject |
Atrial fibrillation |
|
dc.subject |
convolutional neural network |
|
dc.subject |
deep learning |
|
dc.subject |
MRIs |
|
dc.subject |
segmentation |
|
dc.subject |
structural analysis |
|
dc.subject |
FIBROSIS |
|
dc.subject |
IMAGES |
|
dc.subject |
QUANTIFICATION |
|
dc.subject |
MECHANISMS |
|
dc.subject |
VOLUME |
|
dc.subject |
0801 Artificial Intelligence and Image Processing |
|
dc.subject |
Cardiovascular |
|
dc.subject |
Diagnostic Radiology |
|
dc.subject |
Heart Disease |
|
dc.subject |
Cardiovascular |
|
dc.subject |
08 Information and Computing Sciences |
|
dc.subject |
09 Engineering |
|
dc.title |
Fully Automatic Left Atrium Segmentation From Late Gadolinium Enhanced Magnetic Resonance Imaging Using a Dual Fully Convolutional Neural Network. |
|
dc.type |
Journal Article |
|
dc.identifier.doi |
10.1109/tmi.2018.2866845 |
|
pubs.issue |
2 |
|
pubs.begin-page |
515 |
|
pubs.volume |
38 |
|
dc.date.updated |
2021-04-04T21:47:49Z |
|
dc.rights.holder |
Copyright: IEEE |
en |
pubs.author-url |
https://www.ncbi.nlm.nih.gov/pubmed/30716023 |
|
pubs.end-page |
524 |
|
pubs.publication-status |
Published |
|
dc.rights.accessrights |
http://purl.org/eprint/accessRights/OpenAccess |
en |
pubs.subtype |
Research Support, Non-U.S. Gov't |
|
pubs.subtype |
research-article |
|
pubs.subtype |
Journal Article |
|
pubs.subtype |
Research Support, N.I.H., Extramural |
|
pubs.elements-id |
753316 |
|
dc.identifier.eissn |
1558-254X |
|