Difference between revisions of "Publications/zhao.20.icpr.1"

From LRDE
 
(One intermediate revision by the same user not shown)
Line 5: Line 5:
 
| title = FOANet: A Focus of Attention Network with Application to Myocardium Segmentation
  
| title = FOANet: A Focus of Attention Network with Application to Myocardium Segmentation
 
| booktitle = Proceedings of the 25th International Conference on Pattern Recognition (ICPR)
  
| booktitle = Proceedings of the 25th International Conference on Pattern Recognition (ICPR)
  +
| pages = 1120 to 1127
  +
| address = Milan, Italy
  +
| publisher = IEEE
 
| abstract = In myocardium segmentation of cardiac magnetic resonance images, ambiguities often appear near the boundaries of the target domains due to tissue similarities. To address this issue, we propose a new architecture, called FOANet, which can be decomposed in three main steps: a localization stepa Gaussian-based contrast enhancement step, and a segmentation step. This architecture is supplied with a hybrid loss function that guides the FOANet to study the transformation relationship between the input image and the corresponding label in a three-level hierarchy (pixel-patch- and map-level), which is helpful to improve segmentation and recovery of the boundaries. We demonstrate the efficiency of our approach on two public datasets in terms of regional and boundary segmentations.
  
| abstract = In myocardium segmentation of cardiac magnetic resonance images, ambiguities often appear near the boundaries of the target domains due to tissue similarities. To address this issue, we propose a new architecture, called FOANet, which can be decomposed in three main steps: a localization stepa Gaussian-based contrast enhancement step, and a segmentation step. This architecture is supplied with a hybrid loss function that guides the FOANet to study the transformation relationship between the input image and the corresponding label in a three-level hierarchy (pixel-patch- and map-level), which is helpful to improve segmentation and recovery of the boundaries. We demonstrate the efficiency of our approach on two public datasets in terms of regional and boundary segmentations.
 
| lrdepaper = http://www.lrde.epita.fr/dload/papers/zhao.20.icpr.1.pdf
  
| lrdepaper = http://www.lrde.epita.fr/dload/papers/zhao.20.icpr.1.pdf
Line 12: Line 15:
 
| type = inproceedings
  
| type = inproceedings
 
| id = zhao.20.icpr.1
  
| id = zhao.20.icpr.1
  +
| identifier = doi:10.1109/ICPR48806.2021.9412016
 
| bibtex =
 
| bibtex =
 
@InProceedings<nowiki>{</nowiki> zhao.20.icpr.1,
  
@InProceedings<nowiki>{</nowiki> zhao.20.icpr.1,
Line 20: Line 24:
 
booktitle = <nowiki>{</nowiki>Proceedings of the 25th International Conference on
  
booktitle = <nowiki>{</nowiki>Proceedings of the 25th International Conference on
 
Pattern Recognition (ICPR)<nowiki>}</nowiki>,
  
Pattern Recognition (ICPR)<nowiki>}</nowiki>,
−
year = 2020,
 +
year = 2021,
  +
pages = <nowiki>{</nowiki>1120--1127<nowiki>}</nowiki>,
  +
month = jan,
  +
address = <nowiki>{</nowiki>Milan, Italy<nowiki>}</nowiki>,
  +
publisher = <nowiki>{</nowiki>IEEE<nowiki>}</nowiki>,
 
abstract = <nowiki>{</nowiki>In myocardium segmentation of cardiac magnetic resonance
  
abstract = <nowiki>{</nowiki>In myocardium segmentation of cardiac magnetic resonance
 
images, ambiguities often appear near the boundaries of the
  
images, ambiguities often appear near the boundaries of the
Line 34: Line 42:
 
segmentation and recovery of the boundaries. We demonstrate
  
segmentation and recovery of the boundaries. We demonstrate
 
the efficiency of our approach on two public datasets in
  
the efficiency of our approach on two public datasets in
−
terms of regional and boundary segmentations.<nowiki>}</nowiki>
 +
terms of regional and boundary segmentations.<nowiki>}</nowiki>,
  +
doi = <nowiki>{</nowiki>10.1109/ICPR48806.2021.9412016<nowiki>}</nowiki>
 
<nowiki>}</nowiki>
  
<nowiki>}</nowiki>
   

Latest revision as of 10:59, 8 September 2021

Authors
Zhou Zhao, Nicolas Boutry, Élodie Puybareau, Thierry Géraud
Where
Proceedings of the 25th International Conference on Pattern Recognition (ICPR)
Place
Milan, Italy
Type
inproceedings
Publisher
IEEE
Projects
Olena
Keywords
Image
Date
2020-11-02

Abstract

In myocardium segmentation of cardiac magnetic resonance images, ambiguities often appear near the boundaries of the target domains due to tissue similarities. To address this issue, we propose a new architecture, called FOANet, which can be decomposed in three main steps: a localization stepa Gaussian-based contrast enhancement step, and a segmentation step. This architecture is supplied with a hybrid loss function that guides the FOANet to study the transformation relationship between the input image and the corresponding label in a three-level hierarchy (pixel-patch- and map-level), which is helpful to improve segmentation and recovery of the boundaries. We demonstrate the efficiency of our approach on two public datasets in terms of regional and boundary segmentations.

Documents

Bibtex (lrde.bib)

@InProceedings{	  zhao.20.icpr.1,
  author	= {Zhou Zhao and Nicolas Boutry and \'Elodie Puybareau and
		  Thierry G\'eraud},
  title		= {{FOANet}: {A} Focus of Attention Network with Application
		  to Myocardium Segmentation},
  booktitle	= {Proceedings of the 25th International Conference on
		  Pattern Recognition (ICPR)},
  year		= 2021,
  pages		= {1120--1127},
  month		= jan,
  address	= {Milan, Italy},
  publisher	= {IEEE},
  abstract	= {In myocardium segmentation of cardiac magnetic resonance
		  images, ambiguities often appear near the boundaries of the
		  target domains due to tissue similarities. To address this
		  issue, we propose a new architecture, called FOANet, which
		  can be decomposed in three main steps: a localization step,
		  a Gaussian-based contrast enhancement step, and a
		  segmentation step. This architecture is supplied with a
		  hybrid loss function that guides the FOANet to study the
		  transformation relationship between the input image and the
		  corresponding label in a three-level hierarchy (pixel-,
		  patch- and map-level), which is helpful to improve
		  segmentation and recovery of the boundaries. We demonstrate
		  the efficiency of our approach on two public datasets in
		  terms of regional and boundary segmentations.},
  doi		= {10.1109/ICPR48806.2021.9412016}
}





Retrieved from "https://www.lrde.epita.fr/index.php?title=Publications/zhao.20.icpr.1&oldid=126782"