Difference between revisions of "Publications/zhao.20.icpr.2"
From LRDE
(Created page with "{{Publication | published = true | date = 2020-11-02 | authors = Zhou Zhao, Nicolas Boutry, Élodie Puybareau, Thierry Géraud | title = Do not Treat Boundaries and Regions Di...") |
|||
Line 5: | Line 5: | ||
| title = Do not Treat Boundaries and Regions Differently: An Example on Heart Left Atrial Segmentation |
| title = Do not Treat Boundaries and Regions Differently: An Example on Heart Left Atrial Segmentation |
||
| booktitle = Proceedings of the 25th International Conference on Pattern Recognition (ICPR) |
| booktitle = Proceedings of the 25th International Conference on Pattern Recognition (ICPR) |
||
⚫ | | abstract = Atrial fibrillation is the most common heart rhythm disease. Due to a lack of understanding in matter of underlying atrial structures, current treatments are still not satisfying. Recently, with the popularity of deep learning, many segmentation methods based on fully convolutional networks have been proposed to analyze atrial structures, especially from late gadolinium-enhanced magnetic resonance imaging. However, two problems still occur: 1) segmentation results include the atrial- like background; 2) boundaries are very hard to segment. Most segmentation approaches design a specific network that mainly focuses on the regions, to the detriment of the boundaries. Therefore, this paper proposes an attention full convolutional network framework based on the ResNet-101 architecture, which focuses on boundaries as much as on regions. The additional attention module is added to have the network pay more attention on regions and then to reduce the impact of the misleading similarity of neighboring tissues. We also use a hybrid loss composed of a region loss and a boundary loss to treat boundaries and regions at the same time. We demonstrate the efficiency of the proposed approach on the MICCAI 2018 Atrial Segmentation Challenge public dataset. |
||
− | | pages = |
||
⚫ | | abstract = Atrial fibrillation is the most common heart rhythm disease. Due to a lack of understanding in matter of underlying atrial structures, current treatments are still not satisfying. Recently, with the popularity of deep learning, many segmentation methods based on fully convolutional networks have been proposed to analyze atrial structures, especially from late gadolinium-enhanced magnetic resonance imaging. |
||
| lrdepaper = http://www.lrde.epita.fr/dload/papers/zhao.20.icpr.2.pdf |
| lrdepaper = http://www.lrde.epita.fr/dload/papers/zhao.20.icpr.2.pdf |
||
| lrdeprojects = Olena |
| lrdeprojects = Olena |
||
Line 22: | Line 21: | ||
Pattern Recognition (ICPR)<nowiki>}</nowiki>, |
Pattern Recognition (ICPR)<nowiki>}</nowiki>, |
||
year = 2020, |
year = 2020, |
||
− | pages = <nowiki>{</nowiki><nowiki>}</nowiki>, |
||
abstract = <nowiki>{</nowiki>Atrial fibrillation is the most common heart rhythm |
abstract = <nowiki>{</nowiki>Atrial fibrillation is the most common heart rhythm |
||
disease. Due to a lack of understanding in matter of |
disease. Due to a lack of understanding in matter of |
Revision as of 18:21, 9 November 2020
- Authors
- Zhou Zhao, Nicolas Boutry, Élodie Puybareau, Thierry Géraud
- Where
- Proceedings of the 25th International Conference on Pattern Recognition (ICPR)
- Type
- inproceedings
- Projects
- Olena
- Keywords
- Image
- Date
- 2020-11-02
Abstract
Atrial fibrillation is the most common heart rhythm disease. Due to a lack of understanding in matter of underlying atrial structures, current treatments are still not satisfying. Recently, with the popularity of deep learning, many segmentation methods based on fully convolutional networks have been proposed to analyze atrial structures, especially from late gadolinium-enhanced magnetic resonance imaging. However, two problems still occur: 1) segmentation results include the atrial- like background; 2) boundaries are very hard to segment. Most segmentation approaches design a specific network that mainly focuses on the regions, to the detriment of the boundaries. Therefore, this paper proposes an attention full convolutional network framework based on the ResNet-101 architecture, which focuses on boundaries as much as on regions. The additional attention module is added to have the network pay more attention on regions and then to reduce the impact of the misleading similarity of neighboring tissues. We also use a hybrid loss composed of a region loss and a boundary loss to treat boundaries and regions at the same time. We demonstrate the efficiency of the proposed approach on the MICCAI 2018 Atrial Segmentation Challenge public dataset.
Documents
Bibtex (lrde.bib)
@InProceedings{ zhao.20.icpr.2, author = {Zhou Zhao and Nicolas Boutry and \'Elodie Puybareau and Thierry G\'eraud}, title = {Do not Treat Boundaries and Regions Differently: {A}n Example on Heart Left Atrial Segmentation}, booktitle = {Proceedings of the 25th International Conference on Pattern Recognition (ICPR)}, year = 2020, abstract = {Atrial fibrillation is the most common heart rhythm disease. Due to a lack of understanding in matter of underlying atrial structures, current treatments are still not satisfying. Recently, with the popularity of deep learning, many segmentation methods based on fully convolutional networks have been proposed to analyze atrial structures, especially from late gadolinium-enhanced magnetic resonance imaging. However, two problems still occur: 1) segmentation results include the atrial- like background; 2) boundaries are very hard to segment. Most segmentation approaches design a specific network that mainly focuses on the regions, to the detriment of the boundaries. Therefore, this paper proposes an attention full convolutional network framework based on the ResNet-101 architecture, which focuses on boundaries as much as on regions. The additional attention module is added to have the network pay more attention on regions and then to reduce the impact of the misleading similarity of neighboring tissues. We also use a hybrid loss composed of a region loss and a boundary loss to treat boundaries and regions at the same time. We demonstrate the efficiency of the proposed approach on the MICCAI 2018 Atrial Segmentation Challenge public dataset.} }