File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Multi-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge

TitleMulti-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge
Authors
Keywordsdomain adaptation
deep learning
Infant brain segmentation
multi-site issue
low tissue contrast
isointense phase
Issue Date2021
Citation
IEEE Transactions on Medical Imaging, 2021, v. 40, n. 5, p. 1363-1376 How to Cite?
AbstractTo better understand early brain development in health and disorder, it is critical to accurately segment infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Deep learning-based methods have achieved state-of-the-art performance; h owever, one of the major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners. To promote methodological development in the community, the iSeg-2019 challenge (http://iseg2019.web.unc.edu) provides a set of 6-month infant subjects from multiple sites with different protocols/scanners for the participating methods. T raining/validation subjects are from UNC (MAP) and testing subjects are from UNC/UMN (BCP), Stanford University, and Emory University. By the time of writing, there are 30 automatic segmentation methods participated in the iSeg-2019. In this article, 8 top-ranked methods were reviewed by detailing their pipelines/implementations, presenting experimental results, and evaluating performance across different sites in terms of whole brain, regions of interest, and gyral landmark curves. We further pointed out their limitations and possible directions for addressing the multi-site issue. We find that multi-site consistency is still an open issue. We hope that the multi-site dataset in the iSeg-2019 and this review article will attract more researchers to address the challenging and critical multi-site issue in practice.
Persistent Identifierhttp://hdl.handle.net/10722/299487
ISSN
2020 Impact Factor: 10.048
2020 SCImago Journal Rankings: 2.322
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorSun, Yue-
dc.contributor.authorGao, Kun-
dc.contributor.authorWu, Zhengwang-
dc.contributor.authorLi, Guannan-
dc.contributor.authorZong, Xiaopeng-
dc.contributor.authorLei, Zhihao-
dc.contributor.authorWei, Ying-
dc.contributor.authorMa, Jun-
dc.contributor.authorYang, Xiaoping-
dc.contributor.authorFeng, Xue-
dc.contributor.authorZhao, Li-
dc.contributor.authorLe Phan, Trung-
dc.contributor.authorShin, Jitae-
dc.contributor.authorZhong, Tao-
dc.contributor.authorZhang, Yu-
dc.contributor.authorYu, Lequan-
dc.contributor.authorLi, Caizi-
dc.contributor.authorBasnet, Ramesh-
dc.contributor.authorAhmad, M. Omair-
dc.contributor.authorSwamy, M. N.S.-
dc.contributor.authorMa, Wenao-
dc.contributor.authorDou, Qi-
dc.contributor.authorBui, Toan Duc-
dc.contributor.authorNoguera, Camilo Bermudez-
dc.contributor.authorLandman, Bennett-
dc.contributor.authorGotlib, Ian H.-
dc.contributor.authorHumphreys, Kathryn L.-
dc.contributor.authorShultz, Sarah-
dc.contributor.authorLi, Longchuan-
dc.contributor.authorNiu, Sijie-
dc.contributor.authorLin, Weili-
dc.contributor.authorJewells, Valerie-
dc.contributor.authorShen, Dinggang-
dc.contributor.authorLi, Gang-
dc.contributor.authorWang, Li-
dc.date.accessioned2021-05-21T03:34:31Z-
dc.date.available2021-05-21T03:34:31Z-
dc.date.issued2021-
dc.identifier.citationIEEE Transactions on Medical Imaging, 2021, v. 40, n. 5, p. 1363-1376-
dc.identifier.issn0278-0062-
dc.identifier.urihttp://hdl.handle.net/10722/299487-
dc.description.abstractTo better understand early brain development in health and disorder, it is critical to accurately segment infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Deep learning-based methods have achieved state-of-the-art performance; h owever, one of the major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners. To promote methodological development in the community, the iSeg-2019 challenge (http://iseg2019.web.unc.edu) provides a set of 6-month infant subjects from multiple sites with different protocols/scanners for the participating methods. T raining/validation subjects are from UNC (MAP) and testing subjects are from UNC/UMN (BCP), Stanford University, and Emory University. By the time of writing, there are 30 automatic segmentation methods participated in the iSeg-2019. In this article, 8 top-ranked methods were reviewed by detailing their pipelines/implementations, presenting experimental results, and evaluating performance across different sites in terms of whole brain, regions of interest, and gyral landmark curves. We further pointed out their limitations and possible directions for addressing the multi-site issue. We find that multi-site consistency is still an open issue. We hope that the multi-site dataset in the iSeg-2019 and this review article will attract more researchers to address the challenging and critical multi-site issue in practice.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Medical Imaging-
dc.subjectdomain adaptation-
dc.subjectdeep learning-
dc.subjectInfant brain segmentation-
dc.subjectmulti-site issue-
dc.subjectlow tissue contrast-
dc.subjectisointense phase-
dc.titleMulti-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TMI.2021.3055428-
dc.identifier.pmid33507867-
dc.identifier.scopuseid_2-s2.0-85100450936-
dc.identifier.volume40-
dc.identifier.issue5-
dc.identifier.spage1363-
dc.identifier.epage1376-
dc.identifier.eissn1558-254X-
dc.identifier.isiWOS:000645866500006-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats