File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A cascaded nested network for 3T brain MR image segmentation guided by 7T labeling

TitleA cascaded nested network for 3T brain MR image segmentation guided by 7T labeling
Authors
KeywordsBrain segmentation
Cascaded nested network
Deep learning
Magnetic resonance imaging
Issue Date2022
Citation
Pattern Recognition, 2022, v. 124, article no. 108420 How to Cite?
AbstractAccurate segmentation of the brain into gray matter, white matter, and cerebrospinal fluid using magnetic resonance (MR) imaging is critical for visualization and quantification of brain anatomy. Compared to 3T MR images, 7T MR images exhibit higher tissue contrast that is contributive to accurate tissue delineation for training segmentation models. In this paper, we propose a cascaded nested network (CaNes-Net) for segmentation of 3T brain MR images, trained by tissue labels delineated from the corresponding 7T images. We first train a nested network (Nes-Net) for a rough segmentation. The second Nes-Net uses tissue-specific geodesic distance maps as contextual information to refine the segmentation. This process is iterated to build CaNes-Net with a cascade of Nes-Net modules to gradually refine the segmentation. To alleviate the misalignment between 3T and corresponding 7T MR images, we incorporate a correlation coefficient map to allow well-aligned voxels to play a more important role in supervising the training process. We compared CaNes-Net with SPM and FSL tools, as well as four deep learning models on 18 adult subjects and the ADNI dataset. Our results indicate that CaNes-Net reduces segmentation errors caused by the misalignment and improves segmentation accuracy substantially over the competing methods.
Persistent Identifierhttp://hdl.handle.net/10722/325547
ISSN
2023 Impact Factor: 7.5
2023 SCImago Journal Rankings: 2.732
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWei, Jie-
dc.contributor.authorWu, Zhengwang-
dc.contributor.authorWang, Li-
dc.contributor.authorBui, Toan Duc-
dc.contributor.authorQu, Liangqiong-
dc.contributor.authorYap, Pew Thian-
dc.contributor.authorXia, Yong-
dc.contributor.authorLi, Gang-
dc.contributor.authorShen, Dinggang-
dc.date.accessioned2023-02-27T07:34:11Z-
dc.date.available2023-02-27T07:34:11Z-
dc.date.issued2022-
dc.identifier.citationPattern Recognition, 2022, v. 124, article no. 108420-
dc.identifier.issn0031-3203-
dc.identifier.urihttp://hdl.handle.net/10722/325547-
dc.description.abstractAccurate segmentation of the brain into gray matter, white matter, and cerebrospinal fluid using magnetic resonance (MR) imaging is critical for visualization and quantification of brain anatomy. Compared to 3T MR images, 7T MR images exhibit higher tissue contrast that is contributive to accurate tissue delineation for training segmentation models. In this paper, we propose a cascaded nested network (CaNes-Net) for segmentation of 3T brain MR images, trained by tissue labels delineated from the corresponding 7T images. We first train a nested network (Nes-Net) for a rough segmentation. The second Nes-Net uses tissue-specific geodesic distance maps as contextual information to refine the segmentation. This process is iterated to build CaNes-Net with a cascade of Nes-Net modules to gradually refine the segmentation. To alleviate the misalignment between 3T and corresponding 7T MR images, we incorporate a correlation coefficient map to allow well-aligned voxels to play a more important role in supervising the training process. We compared CaNes-Net with SPM and FSL tools, as well as four deep learning models on 18 adult subjects and the ADNI dataset. Our results indicate that CaNes-Net reduces segmentation errors caused by the misalignment and improves segmentation accuracy substantially over the competing methods.-
dc.languageeng-
dc.relation.ispartofPattern Recognition-
dc.subjectBrain segmentation-
dc.subjectCascaded nested network-
dc.subjectDeep learning-
dc.subjectMagnetic resonance imaging-
dc.titleA cascaded nested network for 3T brain MR image segmentation guided by 7T labeling-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.patcog.2021.108420-
dc.identifier.scopuseid_2-s2.0-85121317189-
dc.identifier.volume124-
dc.identifier.spagearticle no. 108420-
dc.identifier.epagearticle no. 108420-
dc.identifier.isiWOS:000736972200011-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats