wmh_seg: Transformer based U-Net for Robust and Automatic White Matter Hyperintensity Segmentation across 1.5T, 3T and 7T
White matter hyperintensity (WMH) remains the top imaging biomarker for neurodegenerative diseases. Robust and accurate segmentation of WMH holds paramount significance for neuroimaging studies. The growing shift from 3T to 7T MRI necessitates robust tools for harmonized segmentation across field st...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
20.02.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | White matter hyperintensity (WMH) remains the top imaging biomarker for neurodegenerative diseases. Robust and accurate segmentation of WMH holds paramount significance for neuroimaging studies. The growing shift from 3T to 7T MRI necessitates robust tools for harmonized segmentation across field strengths and artifacts. Recent deep learning models exhibit promise in WMH segmentation but still face challenges, including diverse training data representation and limited analysis of MRI artifacts' impact. To address these, we introduce wmh_seg, a novel deep learning model leveraging a transformer-based encoder from SegFormer. wmh_seg is trained on an unmatched dataset, including 1.5T, 3T, and 7T FLAIR images from various sources, alongside with artificially added MR artifacts. Our approach bridges gaps in training diversity and artifact analysis. Our model demonstrated stable performance across magnetic field strengths, scanner manufacturers, and common MR imaging artifacts. Despite the unique inhomogeneity artifacts on ultra-high field MR images, our model still offers robust and stable segmentation on 7T FLAIR images. Our model, to date, is the first that offers quality white matter lesion segmentation on 7T FLAIR images. |
---|---|
AbstractList | White matter hyperintensity (WMH) remains the top imaging biomarker for neurodegenerative diseases. Robust and accurate segmentation of WMH holds paramount significance for neuroimaging studies. The growing shift from 3T to 7T MRI necessitates robust tools for harmonized segmentation across field strengths and artifacts. Recent deep learning models exhibit promise in WMH segmentation but still face challenges, including diverse training data representation and limited analysis of MRI artifacts' impact. To address these, we introduce wmh_seg, a novel deep learning model leveraging a transformer-based encoder from SegFormer. wmh_seg is trained on an unmatched dataset, including 1.5T, 3T, and 7T FLAIR images from various sources, alongside with artificially added MR artifacts. Our approach bridges gaps in training diversity and artifact analysis. Our model demonstrated stable performance across magnetic field strengths, scanner manufacturers, and common MR imaging artifacts. Despite the unique inhomogeneity artifacts on ultra-high field MR images, our model still offers robust and stable segmentation on 7T FLAIR images. Our model, to date, is the first that offers quality white matter lesion segmentation on 7T FLAIR images. |
Author | Wu, Minjie Li, Jinghang Huang, Yuanzhe Mettenburg, Joseph M Santini, Tales Aizenstein, Howard J Ibrahim, Tamer S |
Author_xml | – sequence: 1 givenname: Jinghang surname: Li fullname: Li, Jinghang – sequence: 2 givenname: Tales surname: Santini fullname: Santini, Tales – sequence: 3 givenname: Yuanzhe surname: Huang fullname: Huang, Yuanzhe – sequence: 4 givenname: Joseph surname: Mettenburg middlename: M fullname: Mettenburg, Joseph M – sequence: 5 givenname: Tamer surname: Ibrahim middlename: S fullname: Ibrahim, Tamer S – sequence: 6 givenname: Howard surname: Aizenstein middlename: J fullname: Aizenstein, Howard J – sequence: 7 givenname: Minjie surname: Wu fullname: Wu, Minjie |
BookMark | eNqNjEFrwkAUhBdpoVb9Dw-8NiXuJkZ7K6XixR50xWNY41Mj5q3d94Lk33cp_QFlDgMz38yzeiBP2FN9bcwkmWVaP6kR8yVNUz0tdJ6bvuruzblkPL2BDY746EODAfaO8QDb5AsFYgRrv29ZwNEB3lvxjZO6gt25FoSVE4mLZXfDUJMgcS0dbPDUIEnkPIGrgmeGyWtuX8DY35vCDtXj0V0ZR38-UOPFp_1YJrfgv1tkKS--DRSrUs-jimk2z83_qB_EzU5Y |
ContentType | Paper |
Copyright | 2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_29292764953 |
IEDL.DBID | 8FG |
IngestDate | Thu Oct 10 19:38:35 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_29292764953 |
OpenAccessLink | https://www.proquest.com/docview/2929276495?pq-origsite=%requestingapplication% |
PQID | 2929276495 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2929276495 |
PublicationCentury | 2000 |
PublicationDate | 20240220 |
PublicationDateYYYYMMDD | 2024-02-20 |
PublicationDate_xml | – month: 02 year: 2024 text: 20240220 day: 20 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2024 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.5296767 |
SecondaryResourceType | preprint |
Snippet | White matter hyperintensity (WMH) remains the top imaging biomarker for neurodegenerative diseases. Robust and accurate segmentation of WMH holds paramount... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Biomarkers Deep learning Image segmentation Inhomogeneity Magnetic resonance imaging Medical imaging Robustness Transformers |
Title | wmh_seg: Transformer based U-Net for Robust and Automatic White Matter Hyperintensity Segmentation across 1.5T, 3T and 7T |
URI | https://www.proquest.com/docview/2929276495 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB60RfDmEx-1DOjRaJ6bxouopBahpdQUegubZNJemtQkRXLxt7u7pnoQetxdGHaXYb7Z2ZlvAG4SJ5ZmTlIh8lizuUGa0JJYY4kXp4btmHpPViMPR2wwtd9mzqwJuJVNWuXGJipDneSxjJHfmwLHTZcJf_5x9aHJrlHyd7VpobELbUMy4clK8f7rb4zFZK7wmK1_ZlZhR_8A2mO-ouIQdig7gj2VchmXx1B_LhdhSfMHDDbOIxUoUSXBqTaiCsUUTvJoXVYo3vv4tK5yRbCKqqsdDhU1Jg5qSVb8k4le1fhO82VTT5QhVyCIxp0T3KIVKDFucALXfT94GWib_YaNRpXh3_mtU2hleUZngJHFnTQyySbPsTmLvB5RypjtWj2duMXPobNN0sX25UvYNwWEqwJuvQOtqljTlYDgKuqqe-5C-9kfjSdiNPzyvwFDrZIO |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB40RfTmEx9VB_RotM1jk3gRlZaobSg1hd7CJpnUS5PapEj_vbtrqgeh111YlmH4vtnZmW8ArlM7kTAnpRB5olu8TbrwkkRnqZdkbcs2Wq7sRu4HzB9Zr2N7XCfcyrqscoWJCqjTIpE58jtD8LjhMBHPP8w-dTk1Sv6u1iM0NqEhJTddDRpPnWAw_M2yGMwRMbP5D2gVe3R3oTHgM5rvwQbl-7Clii6T8gCWX9OPqKTJPYar8JHmKHklxZEeUIViCYdFvCgrFC9-fFxUhZJYRTXXDvtKHBP9pZQr_qlFr5b4TpNp3VGUI1c0iO1bO7xBM1THOOEhXHU74bOvr-4b1T5VRn8WMI9Ay4ucjgFjk9tZbJBFnm1xFnsuUcaY5Zhui7jJT6C57qTT9duXsO2H_V7UewnezmDHEISu2rlbTdCq-YLOBSFX8UVt9W-0JJOa |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=wmh_seg%3A+Transformer+based+U-Net+for+Robust+and+Automatic+White+Matter+Hyperintensity+Segmentation+across+1.5T%2C+3T+and+7T&rft.jtitle=arXiv.org&rft.au=Li%2C+Jinghang&rft.au=Santini%2C+Tales&rft.au=Huang%2C+Yuanzhe&rft.au=Mettenburg%2C+Joseph+M&rft.date=2024-02-20&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |