Weakly supervised perivascular spaces segmentation with salient guidance of Frangi filter

To develop a weakly supervised 3D perivascular spaces (PVS) segmentation model that combines the filter-based image processing algorithm and the convolutional neural network. We present a weakly supervised learning method for PVS segmentation by combing a rule-based image processing approach Frangi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Magnetic resonance in medicine Ročník 89; číslo 6; s. 2419 - 2431
Hlavní autoři: Lan, Haoyu, Lynch, Kirsten M., Custer, Rachel, Shih, Nien‐Chu, Sherlock, Patrick, Toga, Arthur W., Sepehrband, Farshid, Choupan, Jeiran
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States Wiley Subscription Services, Inc 01.06.2023
Témata:
ISSN:0740-3194, 1522-2594, 1522-2594
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract To develop a weakly supervised 3D perivascular spaces (PVS) segmentation model that combines the filter-based image processing algorithm and the convolutional neural network. We present a weakly supervised learning method for PVS segmentation by combing a rule-based image processing approach Frangi filter with a canonical deep learning algorithm Unet using conditional random field theory. The weighted cross entropy loss function and the training patch selection were implemented for the optimization and to alleviate the class imbalance issue. The performance of the model was evaluated on the Human Connectome Project data. The proposed method increases the true positive rate compared to the rule-based method and reduces the false positive rate by 36% in the weakly supervised training experiment and 39.4% in the supervised training experiment compared to Unet, which results in superior overall performance. In addition, by training the model on manually quality controlled and annotated data which includes the subjects with the presence of white matter hyperintensities, the proposed method differentiates between PVS and white matter hyperintensities, which reduces the false positive rate by 78.5% compared to weakly supervised trained model. Combing the filter-based image processing algorithm and the convolutional neural network algorithm could improve the model's segmentation accuracy, while reducing the training dependence on the large scale annotated PVS mask data by the trained physician. Compared to the filter-based image processing algorithm, the data driven PVS segmentation model using quality-controlled data as the training target could differentiate the white matter hyperintensity from PVS resulting low false positive rate.
AbstractList To develop a weakly supervised 3D perivascular spaces (PVS) segmentation model that combines the filter-based image processing algorithm and the convolutional neural network. We present a weakly supervised learning method for PVS segmentation by combing a rule-based image processing approach Frangi filter with a canonical deep learning algorithm Unet using conditional random field theory. The weighted cross entropy loss function and the training patch selection were implemented for the optimization and to alleviate the class imbalance issue. The performance of the model was evaluated on the Human Connectome Project data. The proposed method increases the true positive rate compared to the rule-based method and reduces the false positive rate by 36% in the weakly supervised training experiment and 39.4% in the supervised training experiment compared to Unet, which results in superior overall performance. In addition, by training the model on manually quality controlled and annotated data which includes the subjects with the presence of white matter hyperintensities, the proposed method differentiates between PVS and white matter hyperintensities, which reduces the false positive rate by 78.5% compared to weakly supervised trained model. Combing the filter-based image processing algorithm and the convolutional neural network algorithm could improve the model's segmentation accuracy, while reducing the training dependence on the large scale annotated PVS mask data by the trained physician. Compared to the filter-based image processing algorithm, the data driven PVS segmentation model using quality-controlled data as the training target could differentiate the white matter hyperintensity from PVS resulting low false positive rate.
To develop a weakly supervised 3D perivascular spaces (PVS) segmentation model that combines the filter-based image processing algorithm and the convolutional neural network.PURPOSETo develop a weakly supervised 3D perivascular spaces (PVS) segmentation model that combines the filter-based image processing algorithm and the convolutional neural network.We present a weakly supervised learning method for PVS segmentation by combing a rule-based image processing approach Frangi filter with a canonical deep learning algorithm Unet using conditional random field theory. The weighted cross entropy loss function and the training patch selection were implemented for the optimization and to alleviate the class imbalance issue. The performance of the model was evaluated on the Human Connectome Project data.METHODSWe present a weakly supervised learning method for PVS segmentation by combing a rule-based image processing approach Frangi filter with a canonical deep learning algorithm Unet using conditional random field theory. The weighted cross entropy loss function and the training patch selection were implemented for the optimization and to alleviate the class imbalance issue. The performance of the model was evaluated on the Human Connectome Project data.The proposed method increases the true positive rate compared to the rule-based method and reduces the false positive rate by 36% in the weakly supervised training experiment and 39.4% in the supervised training experiment compared to Unet, which results in superior overall performance. In addition, by training the model on manually quality controlled and annotated data which includes the subjects with the presence of white matter hyperintensities, the proposed method differentiates between PVS and white matter hyperintensities, which reduces the false positive rate by 78.5% compared to weakly supervised trained model.RESULTSThe proposed method increases the true positive rate compared to the rule-based method and reduces the false positive rate by 36% in the weakly supervised training experiment and 39.4% in the supervised training experiment compared to Unet, which results in superior overall performance. In addition, by training the model on manually quality controlled and annotated data which includes the subjects with the presence of white matter hyperintensities, the proposed method differentiates between PVS and white matter hyperintensities, which reduces the false positive rate by 78.5% compared to weakly supervised trained model.Combing the filter-based image processing algorithm and the convolutional neural network algorithm could improve the model's segmentation accuracy, while reducing the training dependence on the large scale annotated PVS mask data by the trained physician. Compared to the filter-based image processing algorithm, the data driven PVS segmentation model using quality-controlled data as the training target could differentiate the white matter hyperintensity from PVS resulting low false positive rate.CONCLUSIONSCombing the filter-based image processing algorithm and the convolutional neural network algorithm could improve the model's segmentation accuracy, while reducing the training dependence on the large scale annotated PVS mask data by the trained physician. Compared to the filter-based image processing algorithm, the data driven PVS segmentation model using quality-controlled data as the training target could differentiate the white matter hyperintensity from PVS resulting low false positive rate.
Click here for author‐reader discussions
PurposeTo develop a weakly supervised 3D perivascular spaces (PVS) segmentation model that combines the filter‐based image processing algorithm and the convolutional neural network.MethodsWe present a weakly supervised learning method for PVS segmentation by combing a rule‐based image processing approach Frangi filter with a canonical deep learning algorithm Unet using conditional random field theory. The weighted cross entropy loss function and the training patch selection were implemented for the optimization and to alleviate the class imbalance issue. The performance of the model was evaluated on the Human Connectome Project data.ResultsThe proposed method increases the true positive rate compared to the rule‐based method and reduces the false positive rate by 36% in the weakly supervised training experiment and 39.4% in the supervised training experiment compared to Unet, which results in superior overall performance. In addition, by training the model on manually quality controlled and annotated data which includes the subjects with the presence of white matter hyperintensities, the proposed method differentiates between PVS and white matter hyperintensities, which reduces the false positive rate by 78.5% compared to weakly supervised trained model.ConclusionsCombing the filter‐based image processing algorithm and the convolutional neural network algorithm could improve the model's segmentation accuracy, while reducing the training dependence on the large scale annotated PVS mask data by the trained physician. Compared to the filter‐based image processing algorithm, the data driven PVS segmentation model using quality‐controlled data as the training target could differentiate the white matter hyperintensity from PVS resulting low false positive rate.
Author Sepehrband, Farshid
Custer, Rachel
Choupan, Jeiran
Sherlock, Patrick
Shih, Nien‐Chu
Lan, Haoyu
Lynch, Kirsten M.
Toga, Arthur W.
Author_xml – sequence: 1
  givenname: Haoyu
  orcidid: 0000-0002-4398-9053
  surname: Lan
  fullname: Lan, Haoyu
  organization: Laboratory of Neuro Imaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, USC Keck School of Medicine University of Southern California Los Angeles California USA
– sequence: 2
  givenname: Kirsten M.
  surname: Lynch
  fullname: Lynch, Kirsten M.
  organization: Laboratory of Neuro Imaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, USC Keck School of Medicine University of Southern California Los Angeles California USA
– sequence: 3
  givenname: Rachel
  surname: Custer
  fullname: Custer, Rachel
  organization: Laboratory of Neuro Imaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, USC Keck School of Medicine University of Southern California Los Angeles California USA
– sequence: 4
  givenname: Nien‐Chu
  surname: Shih
  fullname: Shih, Nien‐Chu
  organization: Laboratory of Neuro Imaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, USC Keck School of Medicine University of Southern California Los Angeles California USA
– sequence: 5
  givenname: Patrick
  surname: Sherlock
  fullname: Sherlock, Patrick
  organization: Laboratory of Neuro Imaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, USC Keck School of Medicine University of Southern California Los Angeles California USA
– sequence: 6
  givenname: Arthur W.
  surname: Toga
  fullname: Toga, Arthur W.
  organization: Laboratory of Neuro Imaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, USC Keck School of Medicine University of Southern California Los Angeles California USA
– sequence: 7
  givenname: Farshid
  surname: Sepehrband
  fullname: Sepehrband, Farshid
  organization: Laboratory of Neuro Imaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, USC Keck School of Medicine University of Southern California Los Angeles California USA
– sequence: 8
  givenname: Jeiran
  surname: Choupan
  fullname: Choupan, Jeiran
  organization: Laboratory of Neuro Imaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, USC Keck School of Medicine University of Southern California Los Angeles California USA, NeuroScope Inc. New York New York USA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/36692103$$D View this record in MEDLINE/PubMed
BookMark eNpt0btKBDEUBuAgK-5FC19AAjZazJr7TEoRbyDYKGI1ZDMna9a5rMmM4tsbXbUQq4Tw5XD4_ykatV0LCO1TMqeEsJMmNHOmpeZbaEIlYxmTWozQhOSCZJxqMUbTGFeEEK1zsYPGXCnNKOET9PgA5rl-x3FYQ3j1ESqcLv7VRDvUJuC4NhYijrBsoO1N77sWv_n-CUdT-_SCl4OvTGsBdw5fBNMuPXa-7iHsom1n6gh73-cM3V-c351dZTe3l9dnpzeZ5aLoM6OVE4rmBXdKEKmJVdpy0AXjYJWllEnLgDsmQLpFUeXcKqpptZCOOkEsn6Gjzdx16F4GiH3Z-Gihrk0L3RBLlivNc8kkSfTwD111Q2jTdklpmtIpCE3q4FsNiwaqch18Y8J7-RNaAscbYEMXYwD3SygpPwspUyHlVyHJnvyx1m9i7IPx9T8_PgDb6I0y
CitedBy_id crossref_primary_10_1002_jmri_70023
crossref_primary_10_1016_j_neuroimage_2024_120685
crossref_primary_10_1016_j_dsp_2025_105414
crossref_primary_10_1016_j_neuroimage_2025_121297
crossref_primary_10_1016_j_neuroimage_2024_120803
crossref_primary_10_1097_YCO_0000000000000920
crossref_primary_10_1002_alz_13659
crossref_primary_10_1093_braincomms_fcaf200
Cites_doi 10.1016/j.neuroimage.2012.02.018
10.1016/j.media.2020.101692
10.1016/j.neuroimage.2011.09.015
10.1002/ana.24647
10.3389/neuro.11.022.2009
10.1016/j.neuroimage.2018.08.050
10.1109/TPAMI.2017.2699184
10.1016/j.neuroimage.2013.05.041
10.1016/j.neuroimage.2006.01.015
10.1007/978-3-319-24574-4_28
10.1038/s41598-019-48910-x
10.1016/j.media.2018.02.009
10.1016/j.neuroimage.2022.119329
10.1016/j.neuroimage.2012.01.021
10.1007/BFb0056195
10.1109/TBME.2016.2638918
10.1007/3-540-46805-6_19
10.1016/j.neuroimage.2013.04.127
10.1016/j.neuroimage.2018.10.009
10.1002/mrm.28819
10.1016/j.neuroimage.2018.09.060
10.1038/s41598-018-19781-5
10.1038/s41582-020-0312-z
10.1007/s11263-019-01228-7
ContentType Journal Article
Copyright 2023 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
2023. This article is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2023 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
– notice: 2023. This article is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
8FD
FR3
K9.
M7Z
P64
7X8
DOI 10.1002/mrm.29593
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Technology Research Database
Engineering Research Database
ProQuest Health & Medical Complete (Alumni)
Biochemistry Abstracts 1
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Biochemistry Abstracts 1
ProQuest Health & Medical Complete (Alumni)
Engineering Research Database
Technology Research Database
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitleList MEDLINE
MEDLINE - Academic
CrossRef
Biochemistry Abstracts 1
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Physics
EISSN 1522-2594
EndPage 2431
ExternalDocumentID 36692103
10_1002_mrm_29593
Genre Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: NIA NIH HHS
  grantid: R41 AG073024
– fundername: NIA NIH HHS
  grantid: P30 AG066530
– fundername: NIA NIH HHS
  grantid: T32 AG058507
– fundername: NIMH NIH HHS
  grantid: RF1 MH123223
– fundername: NIA NIH HHS
  grantid: R01 AG070825
GroupedDBID ---
-DZ
.3N
.55
.GA
.Y3
05W
0R~
10A
1L6
1OB
1OC
1ZS
31~
33P
3O-
3SF
3WU
4.4
4ZD
50Y
50Z
51W
51X
52M
52N
52O
52P
52R
52S
52T
52U
52V
52W
52X
53G
5GY
5RE
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A01
A03
AAESR
AAEVG
AAHQN
AAIPD
AAMMB
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAYXX
AAZKR
ABCQN
ABCUV
ABDPE
ABEML
ABIJN
ABJNI
ABLJU
ABPVW
ABQWH
ABXGK
ACAHQ
ACBWZ
ACCZN
ACFBH
ACGFO
ACGFS
ACGOF
ACIWK
ACMXC
ACPOU
ACPRK
ACRPL
ACSCC
ACXBN
ACXQS
ACYXJ
ADBBV
ADBTR
ADEOM
ADIZJ
ADKYN
ADMGS
ADNMO
ADOZA
ADXAS
ADZMN
AEFGJ
AEGXH
AEIGN
AEIMD
AENEX
AEUYR
AEYWJ
AFBPY
AFFNX
AFFPM
AFGKR
AFRAH
AFWVQ
AFZJQ
AGHNM
AGQPQ
AGXDD
AGYGG
AHBTC
AHMBA
AIACR
AIAGR
AIDQK
AIDYY
AIQQE
AITYG
AIURR
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ASPBG
ATUGU
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMXJE
BROTX
BRXPI
BY8
C45
CITATION
CS3
D-6
D-7
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRMAN
DRSTM
DU5
EBD
EBS
EJD
EMOBN
F00
F01
F04
FEDTE
FUBAC
G-S
G.N
GNP
GODZA
H.X
HBH
HDBZQ
HF~
HGLYW
HHY
HHZ
HVGLF
HZ~
I-F
IX1
J0M
JPC
KBYEO
KQQ
LATKE
LAW
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
M65
MEWTI
MK4
MRFUL
MRMAN
MRSTM
MSFUL
MSMAN
MSSTM
MXFUL
MXMAN
MXSTM
N04
N05
N9A
NF~
NNB
O66
O8X
O9-
OIG
OVD
P2P
P2W
P2X
P2Z
P4B
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
QRW
R.K
RIWAO
RJQFR
ROL
RX1
RYL
SAMSI
SUPJJ
SV3
TEORI
TUS
TWZ
UB1
V2E
V8K
W8V
W99
WBKPD
WHWMO
WIB
WIH
WIJ
WIK
WIN
WJL
WOHZO
WQJ
WVDHM
WXI
WXSBR
X7M
XG1
XPP
XV2
ZGI
ZXP
ZZTAW
~IA
~WT
CGR
CUY
CVF
ECM
EIF
NPM
8FD
FR3
K9.
M7Z
P64
7X8
ID FETCH-LOGICAL-c348t-a96f461783f640590c69c3e9823ec6c1125c2e3f24e5fb8d73c6191db5f1f40c3
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000917691800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0740-3194
1522-2594
IngestDate Thu Oct 02 04:17:07 EDT 2025
Sat Nov 29 14:44:59 EST 2025
Mon Jul 21 05:27:57 EDT 2025
Sat Nov 29 06:34:36 EST 2025
Tue Nov 18 22:30:52 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 6
Keywords conditional random field
image processing
perivascular spaces
structural MRI
convolutional neural network
Language English
License 2023 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c348t-a96f461783f640590c69c3e9823ec6c1125c2e3f24e5fb8d73c6191db5f1f40c3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-4398-9053
OpenAccessLink https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/mrm.29593
PMID 36692103
PQID 2791099801
PQPubID 1016391
PageCount 13
ParticipantIDs proquest_miscellaneous_2769375250
proquest_journals_2791099801
pubmed_primary_36692103
crossref_primary_10_1002_mrm_29593
crossref_citationtrail_10_1002_mrm_29593
PublicationCentury 2000
PublicationDate 2023-06-00
20230601
PublicationDateYYYYMMDD 2023-06-01
PublicationDate_xml – month: 06
  year: 2023
  text: 2023-06-00
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Hoboken
PublicationTitle Magnetic resonance in medicine
PublicationTitleAlternate Magn Reson Med
PublicationYear 2023
Publisher Wiley Subscription Services, Inc
Publisher_xml – name: Wiley Subscription Services, Inc
References e_1_2_9_30_1
e_1_2_9_31_1
e_1_2_9_11_1
e_1_2_9_34_1
e_1_2_9_10_1
e_1_2_9_35_1
e_1_2_9_13_1
e_1_2_9_12_1
Zheng S (e_1_2_9_16_1)
Abadi M (e_1_2_9_36_1) 2016
Boutinaud P (e_1_2_9_5_1) 2021
Ioffe S (e_1_2_9_32_1) 2015
Srivastava N (e_1_2_9_33_1) 2014; 15
e_1_2_9_15_1
e_1_2_9_38_1
e_1_2_9_14_1
e_1_2_9_37_1
e_1_2_9_19_1
Vaswani A (e_1_2_9_20_1) 2017
e_1_2_9_22_1
e_1_2_9_21_1
e_1_2_9_24_1
e_1_2_9_23_1
e_1_2_9_8_1
e_1_2_9_7_1
e_1_2_9_6_1
e_1_2_9_4_1
e_1_2_9_3_1
e_1_2_9_2_1
Krähenbühl P (e_1_2_9_17_1) 2011
e_1_2_9_9_1
Monteiro M (e_1_2_9_18_1) 2018
e_1_2_9_26_1
e_1_2_9_25_1
e_1_2_9_28_1
e_1_2_9_27_1
e_1_2_9_29_1
References_xml – volume: 15
  start-page: 1929
  year: 2014
  ident: e_1_2_9_33_1
  article-title: Dropout: a simple way to prevent neural networks from overfitting
  publication-title: J Mach Learn Res
– ident: e_1_2_9_25_1
  doi: 10.1016/j.neuroimage.2012.02.018
– ident: e_1_2_9_24_1
  doi: 10.1016/j.media.2020.101692
– ident: e_1_2_9_30_1
  doi: 10.1016/j.neuroimage.2011.09.015
– start-page: 1529
  volume-title: Proceedings of the IEEE International Conference on Computer Vision
  ident: e_1_2_9_16_1
– ident: e_1_2_9_9_1
  doi: 10.1002/ana.24647
– ident: e_1_2_9_27_1
  doi: 10.3389/neuro.11.022.2009
– ident: e_1_2_9_11_1
  doi: 10.1016/j.neuroimage.2018.08.050
– ident: e_1_2_9_14_1
  doi: 10.1109/TPAMI.2017.2699184
– ident: e_1_2_9_12_1
  doi: 10.1016/j.neuroimage.2013.05.041
– ident: e_1_2_9_31_1
  doi: 10.1016/j.neuroimage.2006.01.015
– ident: e_1_2_9_22_1
  doi: 10.1007/978-3-319-24574-4_28
– ident: e_1_2_9_3_1
  doi: 10.1038/s41598-019-48910-x
– year: 2017
  ident: e_1_2_9_20_1
  article-title: Attention is all you need
  publication-title: Adv Neural Inf Process Syst
– ident: e_1_2_9_7_1
  doi: 10.1016/j.media.2018.02.009
– year: 2018
  ident: e_1_2_9_18_1
  publication-title: Conditional Random Fields as Recurrent Neural Networks for 3D Medical Imaging Segmentation
– ident: e_1_2_9_23_1
  doi: 10.1016/j.neuroimage.2022.119329
– ident: e_1_2_9_29_1
  doi: 10.1016/j.neuroimage.2012.01.021
– ident: e_1_2_9_35_1
– ident: e_1_2_9_10_1
  doi: 10.1007/BFb0056195
– start-page: 265
  volume-title: 12th USENIX Symposium on Operating Systems Design and Implementation
  year: 2016
  ident: e_1_2_9_36_1
– ident: e_1_2_9_8_1
– start-page: 448
  volume-title: International Conference on Machine Learning
  year: 2015
  ident: e_1_2_9_32_1
– ident: e_1_2_9_6_1
  doi: 10.1109/TBME.2016.2638918
– start-page: 29
  year: 2021
  ident: e_1_2_9_5_1
  article-title: 3D segmentation of perivascular spaces on T1‐weighted 3 Tesla MR images with a convolutional autoencoder and a U‐shaped neural network
  publication-title: Front Neuroinform
– ident: e_1_2_9_15_1
– ident: e_1_2_9_19_1
  doi: 10.1007/3-540-46805-6_19
– ident: e_1_2_9_28_1
  doi: 10.1016/j.neuroimage.2013.04.127
– ident: e_1_2_9_13_1
  doi: 10.1016/j.neuroimage.2018.10.009
– ident: e_1_2_9_21_1
  doi: 10.1002/mrm.28819
– ident: e_1_2_9_37_1
– ident: e_1_2_9_34_1
– volume-title: Adv Neural Inf Process Syst
  year: 2011
  ident: e_1_2_9_17_1
– ident: e_1_2_9_26_1
  doi: 10.1016/j.neuroimage.2018.09.060
– ident: e_1_2_9_4_1
  doi: 10.1038/s41598-018-19781-5
– ident: e_1_2_9_2_1
  doi: 10.1038/s41582-020-0312-z
– ident: e_1_2_9_38_1
  doi: 10.1007/s11263-019-01228-7
SSID ssj0009974
Score 2.481692
Snippet Click here for author‐reader discussions
To develop a weakly supervised 3D perivascular spaces (PVS) segmentation model that combines the filter-based image processing algorithm and the convolutional...
PurposeTo develop a weakly supervised 3D perivascular spaces (PVS) segmentation model that combines the filter‐based image processing algorithm and the...
SourceID proquest
pubmed
crossref
SourceType Aggregation Database
Index Database
Enrichment Source
StartPage 2419
SubjectTerms Algorithms
Artificial neural networks
Conditional random fields
Deep learning
Entropy (Information theory)
Field theory
Humans
Image filters
Image processing
Image Processing, Computer-Assisted - methods
Image segmentation
Machine learning
Magnetic Resonance Imaging - methods
Model accuracy
Neural networks
Neural Networks, Computer
Optimization
Substantia alba
Supervised learning
Training
Title Weakly supervised perivascular spaces segmentation with salient guidance of Frangi filter
URI https://www.ncbi.nlm.nih.gov/pubmed/36692103
https://www.proquest.com/docview/2791099801
https://www.proquest.com/docview/2769375250
Volume 89
WOSCitedRecordID wos000917691800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library Free Content
  customDbUrl:
  eissn: 1522-2594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0009974
  issn: 0740-3194
  databaseCode: WIN
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
– providerCode: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1522-2594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0009974
  issn: 0740-3194
  databaseCode: DRFUL
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLbYBtNeEIzLCmMyiAcklLHYzsWPqDBNokxobKI8RYljtxGrWzXNtP57jmPnMo1J8MBLFNlOI_l8PfmOffwdhN7mOXznMsU9ojLlsSjIvczcicyXvp_l4ABrdf1RdHoaj8f8m1tVKutyApHW8fU1X_xXU0MbGNscnf0Hc7c_Cg1wD0aHK5gdrn9l-B8y_XW5fl9WC-MGSiCURsy4zTgFD2KSsEo5mbljR9rlqQMjN4kBk6rI63MEQCMNrZ0URrypyeJtij-lEy2t_LPh8mZ4oW9t1I_s6upJOl9Xbdta2-pTXwognlJ3y7HDqqkScmZUptvUj-_TYmpBK7U3nFb9hQpCu4SqQ-mcKwS-EG6xvve1BYQcym64UmZ96S0fbzVjZ8vZITGqyv0xYInFrLYrDUMO0SztPnNt8mHTtYG2SBRwcIVbn86OL0adVjPEWI0I1RH50L5pB203z95kMXeEJjVFOX-EHrrYAn-0mHiM7km9i7a_OqPsogd1uq8on6CfFiS4AwnugwRbkOA-SLABCXYgwQ1I8FxhCxJsQfIUXRx_Ph-eeK7Ihicoi1deykPFzDlRqkJmTiKLkAsqeUyoFKEAOh4IIqkiTAYqi_OICoi5_TwLlK_YkaDP0Kaea7mHMEnzIA1iTkjOmYgUlyyNlIjhIaCNqRygd82kJcIp0JtCKJeJ1c4mCUx1Uk_1AL1phy6s7MqfBu03M5-4P2CZkIibzV4gXgP0uu0Gn2k2wlIt55UZEwIrNxv6A_TcWqx9S2PhF3f2vEQ7Hbz30eZqWclX6L64WhXl8gBtROP4wEHqN2fMl5M
linkProvider Wiley-Blackwell
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=Weakly+supervised+perivascular+spaces+segmentation+with+salient+guidance+of+Frangi+filter&rft.jtitle=Magnetic+resonance+in+medicine&rft.au=Lan%2C+Haoyu&rft.au=Lynch%2C+Kirsten+M&rft.au=Custer%2C+Rachel&rft.au=Shih%2C+Nien-Chu&rft.date=2023-06-01&rft.eissn=1522-2594&rft.volume=89&rft.issue=6&rft.spage=2419&rft_id=info:doi/10.1002%2Fmrm.29593&rft_id=info%3Apmid%2F36692103&rft.externalDocID=36692103
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0740-3194&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0740-3194&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0740-3194&client=summon