File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Automatic 3D cardiovascular MR segmentation with densely-connected volumetric convnets

TitleAutomatic 3D cardiovascular MR segmentation with densely-connected volumetric convnets
Authors
Issue Date2017
PublisherSpringer.
Citation
20th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2017), Quebec City, Canada, 11-13 September 2017. In Descoteaux, M, Maier-Hein, L, Franz, A, et al. (Eds.), Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II, p. 287-295. Cham, Switzerland: Springer, 2017 How to Cite?
AbstractAutomatic and accurate whole-heart and great vessel segmentation from 3D cardiac magnetic resonance (MR) images plays an important role in the computer-assisted diagnosis and treatment of cardiovascular disease. However, this task is very challenging due to ambiguous cardiac borders and large anatomical variations among different subjects. In this paper, we propose a novel densely-connected volumetric convolutional neural network, referred as DenseVoxNet, to automatically segment the cardiac and vascular structures from 3D cardiac MR images. The DenseVoxNet adopts the 3D fully convolutional architecture for effective volume-to-volume prediction. From the learning perspective, our DenseVoxNet has three compelling advantages. First, it preserves the maximum information flow between layers by a densely-connected mechanism and hence eases the network training. Second, it avoids learning redundant feature maps by encouraging feature reuse and hence requires fewer parameters to achieve high performance, which is essential for medical applications with limited training data. Third, we add auxiliary side paths to strengthen the gradient propagation and stabilize the learning process. We demonstrate the effectiveness of DenseVoxNet by comparing it with the state-of-the-art approaches from HVSMR 2016 challenge in conjunction with MICCAI, and our network achieves the best dice coefficient. We also show that our network can achieve better performance than other 3D ConvNets but with fewer parameters.
Persistent Identifierhttp://hdl.handle.net/10722/299558
ISBN
ISSN
2023 SCImago Journal Rankings: 0.606
Series/Report no.Lecture Notes in Computer Science ; 10434

 

DC FieldValueLanguage
dc.contributor.authorYu, Lequan-
dc.contributor.authorCheng, Jie Zhi-
dc.contributor.authorDou, Qi-
dc.contributor.authorYang, Xin-
dc.contributor.authorChen, Hao-
dc.contributor.authorQin, Jing-
dc.contributor.authorHeng, Pheng Ann-
dc.date.accessioned2021-05-21T03:34:40Z-
dc.date.available2021-05-21T03:34:40Z-
dc.date.issued2017-
dc.identifier.citation20th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2017), Quebec City, Canada, 11-13 September 2017. In Descoteaux, M, Maier-Hein, L, Franz, A, et al. (Eds.), Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II, p. 287-295. Cham, Switzerland: Springer, 2017-
dc.identifier.isbn9783319661841-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/299558-
dc.description.abstractAutomatic and accurate whole-heart and great vessel segmentation from 3D cardiac magnetic resonance (MR) images plays an important role in the computer-assisted diagnosis and treatment of cardiovascular disease. However, this task is very challenging due to ambiguous cardiac borders and large anatomical variations among different subjects. In this paper, we propose a novel densely-connected volumetric convolutional neural network, referred as DenseVoxNet, to automatically segment the cardiac and vascular structures from 3D cardiac MR images. The DenseVoxNet adopts the 3D fully convolutional architecture for effective volume-to-volume prediction. From the learning perspective, our DenseVoxNet has three compelling advantages. First, it preserves the maximum information flow between layers by a densely-connected mechanism and hence eases the network training. Second, it avoids learning redundant feature maps by encouraging feature reuse and hence requires fewer parameters to achieve high performance, which is essential for medical applications with limited training data. Third, we add auxiliary side paths to strengthen the gradient propagation and stabilize the learning process. We demonstrate the effectiveness of DenseVoxNet by comparing it with the state-of-the-art approaches from HVSMR 2016 challenge in conjunction with MICCAI, and our network achieves the best dice coefficient. We also show that our network can achieve better performance than other 3D ConvNets but with fewer parameters.-
dc.languageeng-
dc.publisherSpringer.-
dc.relation.ispartofMedical Image Computing and Computer-Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings-
dc.relation.ispartofseriesLecture Notes in Computer Science ; 10434-
dc.titleAutomatic 3D cardiovascular MR segmentation with densely-connected volumetric convnets-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/978-3-319-66185-8_33-
dc.identifier.scopuseid_2-s2.0-85029509897-
dc.identifier.spage287-
dc.identifier.epage295-
dc.identifier.eissn1611-3349-
dc.publisher.placeCham, Switzerland-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats