File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images

TitleVoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images
Authors
KeywordsBrain segmentation
Auto-context
3D deep learning
Multi-level contextual information
Residual learning
Multi-modality
Convolutional neural network
Issue Date2018
Citation
NeuroImage, 2018, v. 170, p. 446-455 How to Cite?
AbstractSegmentation of key brain tissues from 3D medical images is of great significance for brain disease diagnosis, progression assessment and monitoring of neurologic conditions. While manual segmentation is time-consuming, laborious, and subjective, automated segmentation is quite challenging due to the complicated anatomical environment of brain and the large variations of brain tissues. We propose a novel voxelwise residual network (VoxResNet) with a set of effective training schemes to cope with this challenging problem. The main merit of residual learning is that it can alleviate the degradation problem when training a deep network so that the performance gains achieved by increasing the network depth can be fully leveraged. With this technique, our VoxResNet is built with 25 layers, and hence can generate more representative features to deal with the large variations of brain tissues than its rivals using hand-crafted features or shallower networks. In order to effectively train such a deep network with limited training data for brain segmentation, we seamlessly integrate multi-modality and multi-level contextual information into our network, so that the complementary information of different modalities can be harnessed and features of different scales can be exploited. Furthermore, an auto-context version of the VoxResNet is proposed by combining the low-level image appearance features, implicit shape information, and high-level context together for further improving the segmentation performance. Extensive experiments on the well-known benchmark (i.e., MRBrainS) of brain segmentation from 3D magnetic resonance (MR) images corroborated the efficacy of the proposed VoxResNet. Our method achieved the first place in the challenge out of 37 competitors including several state-of-the-art brain segmentation methods. Our method is inherently general and can be readily applied as a powerful tool to many brain-related studies, where accurate segmentation of brain structures is critical.
Persistent Identifierhttp://hdl.handle.net/10722/299546
ISSN
2023 Impact Factor: 4.7
2023 SCImago Journal Rankings: 2.436
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorChen, Hao-
dc.contributor.authorDou, Qi-
dc.contributor.authorYu, Lequan-
dc.contributor.authorQin, Jing-
dc.contributor.authorHeng, Pheng Ann-
dc.date.accessioned2021-05-21T03:34:38Z-
dc.date.available2021-05-21T03:34:38Z-
dc.date.issued2018-
dc.identifier.citationNeuroImage, 2018, v. 170, p. 446-455-
dc.identifier.issn1053-8119-
dc.identifier.urihttp://hdl.handle.net/10722/299546-
dc.description.abstractSegmentation of key brain tissues from 3D medical images is of great significance for brain disease diagnosis, progression assessment and monitoring of neurologic conditions. While manual segmentation is time-consuming, laborious, and subjective, automated segmentation is quite challenging due to the complicated anatomical environment of brain and the large variations of brain tissues. We propose a novel voxelwise residual network (VoxResNet) with a set of effective training schemes to cope with this challenging problem. The main merit of residual learning is that it can alleviate the degradation problem when training a deep network so that the performance gains achieved by increasing the network depth can be fully leveraged. With this technique, our VoxResNet is built with 25 layers, and hence can generate more representative features to deal with the large variations of brain tissues than its rivals using hand-crafted features or shallower networks. In order to effectively train such a deep network with limited training data for brain segmentation, we seamlessly integrate multi-modality and multi-level contextual information into our network, so that the complementary information of different modalities can be harnessed and features of different scales can be exploited. Furthermore, an auto-context version of the VoxResNet is proposed by combining the low-level image appearance features, implicit shape information, and high-level context together for further improving the segmentation performance. Extensive experiments on the well-known benchmark (i.e., MRBrainS) of brain segmentation from 3D magnetic resonance (MR) images corroborated the efficacy of the proposed VoxResNet. Our method achieved the first place in the challenge out of 37 competitors including several state-of-the-art brain segmentation methods. Our method is inherently general and can be readily applied as a powerful tool to many brain-related studies, where accurate segmentation of brain structures is critical.-
dc.languageeng-
dc.relation.ispartofNeuroImage-
dc.subjectBrain segmentation-
dc.subjectAuto-context-
dc.subject3D deep learning-
dc.subjectMulti-level contextual information-
dc.subjectResidual learning-
dc.subjectMulti-modality-
dc.subjectConvolutional neural network-
dc.titleVoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.neuroimage.2017.04.041-
dc.identifier.pmid28445774-
dc.identifier.scopuseid_2-s2.0-85018171435-
dc.identifier.volume170-
dc.identifier.spage446-
dc.identifier.epage455-
dc.identifier.eissn1095-9572-
dc.identifier.isiWOS:000429940900036-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats