An attention residual u-net with differential preprocessing and geometric postprocessing: Learning how to segment vasculature including intracranial aneurysms

•This paper proposes automatically segmenting vasculature, including intracranial aneurysms, from 3DRA images with the need for “patient-specific” computational hemodynamics.•An attention residual U-Net with preprocessing and postprocessing is constructed.•We design multi-scale supervision to improv...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Medical image analysis Jg. 84; S. 102697
Hauptverfasser: Mu, Nan, Lyu, Zonghan, Rezaeitaleshmahalleh, Mostafa, Tang, Jinshan, Jiang, Jingfeng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Netherlands Elsevier B.V 01.02.2023
Schlagworte:
ISSN:1361-8415, 1361-8423, 1361-8423
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract •This paper proposes automatically segmenting vasculature, including intracranial aneurysms, from 3DRA images with the need for “patient-specific” computational hemodynamics.•An attention residual U-Net with preprocessing and postprocessing is constructed.•We design multi-scale supervision to improve the segmentation of small vessels.•We adopt a fully connected 3D conditional random field to remove unwanted vessel-to-vessel or vessel-to-aneurysm connections.•This is the first study to systematically investigate the potential of deep-learning image segmentation for “patient-specific” computational hemodynamics. Intracranial aneurysms (IA) are lethal, with high morbidity and mortality rates. Reliable, rapid, and accurate segmentation of IAs and their adjacent vasculature from medical imaging data is important to improve the clinical management of patients with IAs. However, due to the blurred boundaries and complex structure of IAs and overlapping with brain tissue or other cerebral arteries, image segmentation of IAs remains challenging. This study aimed to develop an attention residual U-Net (ARU-Net) architecture with differential preprocessing and geometric postprocessing for automatic segmentation of IAs and their adjacent arteries in conjunction with 3D rotational angiography (3DRA) images. The proposed ARU-Net followed the classic U-Net framework with the following key enhancements. First, we preprocessed the 3DRA images based on boundary enhancement to capture more contour information and enhance the presence of small vessels. Second, we introduced the long skip connections of the attention gate at each layer of the fully convolutional decoder-encoder structure to emphasize the field of view (FOV) for IAs. Third, residual-based short skip connections were also embedded in each layer to implement in-depth supervision to help the network converge. Fourth, we devised a multiscale supervision strategy for independent prediction at different levels of the decoding path, integrating multiscale semantic information to facilitate the segmentation of small vessels. Fifth, the 3D conditional random field (3DCRF) and 3D connected component optimization (3DCCO) were exploited as postprocessing to optimize the segmentation results. Comprehensive experimental assessments validated the effectiveness of our ARU-Net. The proposed ARU-Net model achieved comparable or superior performance to the state-of-the-art methods through quantitative and qualitative evaluations. Notably, we found that ARU-Net improved the identification of arteries connecting to an IA, including small arteries that were hard to recognize by other methods. Consequently, IA geometries segmented by the proposed ARU-Net model yielded superior performance during subsequent computational hemodynamic studies (also known as "patient-specific" computational fluid dynamics [CFD] simulations). Furthermore, in an ablation study, the five key enhancements mentioned above were confirmed. The proposed ARU-Net model can automatically segment the IAs in 3DRA images with relatively high accuracy and potentially has significant value for clinical computational hemodynamic analysis. [Display omitted]
AbstractList Intracranial aneurysms (IA) are lethal, with high morbidity and mortality rates. Reliable, rapid, and accurate segmentation of IAs and their adjacent vasculature from medical imaging data is important to improve the clinical management of patients with IAs. However, due to the blurred boundaries and complex structure of IAs and overlapping with brain tissue or other cerebral arteries, image segmentation of IAs remains challenging. This study aimed to develop an attention residual U-Net (ARU-Net) architecture with differential preprocessing and geometric postprocessing for automatic segmentation of IAs and their adjacent arteries in conjunction with 3D rotational angiography (3DRA) images.OBJECTIVEIntracranial aneurysms (IA) are lethal, with high morbidity and mortality rates. Reliable, rapid, and accurate segmentation of IAs and their adjacent vasculature from medical imaging data is important to improve the clinical management of patients with IAs. However, due to the blurred boundaries and complex structure of IAs and overlapping with brain tissue or other cerebral arteries, image segmentation of IAs remains challenging. This study aimed to develop an attention residual U-Net (ARU-Net) architecture with differential preprocessing and geometric postprocessing for automatic segmentation of IAs and their adjacent arteries in conjunction with 3D rotational angiography (3DRA) images.The proposed ARU-Net followed the classic U-Net framework with the following key enhancements. First, we preprocessed the 3DRA images based on boundary enhancement to capture more contour information and enhance the presence of small vessels. Second, we introduced the long skip connections of the attention gate at each layer of the fully convolutional decoder-encoder structure to emphasize the field of view (FOV) for IAs. Third, residual-based short skip connections were also embedded in each layer to implement in-depth supervision to help the network converge. Fourth, we devised a multiscale supervision strategy for independent prediction at different levels of the decoding path, integrating multiscale semantic information to facilitate the segmentation of small vessels. Fifth, the 3D conditional random field (3DCRF) and 3D connected component optimization (3DCCO) were exploited as postprocessing to optimize the segmentation results.METHODSThe proposed ARU-Net followed the classic U-Net framework with the following key enhancements. First, we preprocessed the 3DRA images based on boundary enhancement to capture more contour information and enhance the presence of small vessels. Second, we introduced the long skip connections of the attention gate at each layer of the fully convolutional decoder-encoder structure to emphasize the field of view (FOV) for IAs. Third, residual-based short skip connections were also embedded in each layer to implement in-depth supervision to help the network converge. Fourth, we devised a multiscale supervision strategy for independent prediction at different levels of the decoding path, integrating multiscale semantic information to facilitate the segmentation of small vessels. Fifth, the 3D conditional random field (3DCRF) and 3D connected component optimization (3DCCO) were exploited as postprocessing to optimize the segmentation results.Comprehensive experimental assessments validated the effectiveness of our ARU-Net. The proposed ARU-Net model achieved comparable or superior performance to the state-of-the-art methods through quantitative and qualitative evaluations. Notably, we found that ARU-Net improved the identification of arteries connecting to an IA, including small arteries that were hard to recognize by other methods. Consequently, IA geometries segmented by the proposed ARU-Net model yielded superior performance during subsequent computational hemodynamic studies (also known as "patient-specific" computational fluid dynamics [CFD] simulations). Furthermore, in an ablation study, the five key enhancements mentioned above were confirmed.RESULTSComprehensive experimental assessments validated the effectiveness of our ARU-Net. The proposed ARU-Net model achieved comparable or superior performance to the state-of-the-art methods through quantitative and qualitative evaluations. Notably, we found that ARU-Net improved the identification of arteries connecting to an IA, including small arteries that were hard to recognize by other methods. Consequently, IA geometries segmented by the proposed ARU-Net model yielded superior performance during subsequent computational hemodynamic studies (also known as "patient-specific" computational fluid dynamics [CFD] simulations). Furthermore, in an ablation study, the five key enhancements mentioned above were confirmed.The proposed ARU-Net model can automatically segment the IAs in 3DRA images with relatively high accuracy and potentially has significant value for clinical computational hemodynamic analysis.CONCLUSIONSThe proposed ARU-Net model can automatically segment the IAs in 3DRA images with relatively high accuracy and potentially has significant value for clinical computational hemodynamic analysis.
Intracranial aneurysms (IA) are lethal, with high morbidity and mortality rates. Reliable, rapid, and accurate segmentation of IAs and their adjacent vasculature from medical imaging data is important to improve the clinical management of patients with IAs. However, due to the blurred boundaries and complex structure of IAs and overlapping with brain tissue or other cerebral arteries, image segmentation of IAs remains challenging. This study aimed to develop an attention residual U-Net (ARU-Net) architecture with differential preprocessing and geometric postprocessing for automatic segmentation of IAs and their adjacent arteries in conjunction with 3D rotational angiography (3DRA) images. The proposed ARU-Net followed the classic U-Net framework with the following key enhancements. First, we preprocessed the 3DRA images based on boundary enhancement to capture more contour information and enhance the presence of small vessels. Second, we introduced the long skip connections of the attention gate at each layer of the fully convolutional decoder-encoder structure to emphasize the field of view (FOV) for IAs. Third, residual-based short skip connections were also embedded in each layer to implement in-depth supervision to help the network converge. Fourth, we devised a multiscale supervision strategy for independent prediction at different levels of the decoding path, integrating multiscale semantic information to facilitate the segmentation of small vessels. Fifth, the 3D conditional random field (3DCRF) and 3D connected component optimization (3DCCO) were exploited as postprocessing to optimize the segmentation results. Comprehensive experimental assessments validated the effectiveness of our ARU-Net. The proposed ARU-Net model achieved comparable or superior performance to the state-of-the-art methods through quantitative and qualitative evaluations. Notably, we found that ARU-Net improved the identification of arteries connecting to an IA, including small arteries that were hard to recognize by other methods. Consequently, IA geometries segmented by the proposed ARU-Net model yielded superior performance during subsequent computational hemodynamic studies (also known as "patient-specific" computational fluid dynamics [CFD] simulations). Furthermore, in an ablation study, the five key enhancements mentioned above were confirmed. The proposed ARU-Net model can automatically segment the IAs in 3DRA images with relatively high accuracy and potentially has significant value for clinical computational hemodynamic analysis.
•This paper proposes automatically segmenting vasculature, including intracranial aneurysms, from 3DRA images with the need for “patient-specific” computational hemodynamics.•An attention residual U-Net with preprocessing and postprocessing is constructed.•We design multi-scale supervision to improve the segmentation of small vessels.•We adopt a fully connected 3D conditional random field to remove unwanted vessel-to-vessel or vessel-to-aneurysm connections.•This is the first study to systematically investigate the potential of deep-learning image segmentation for “patient-specific” computational hemodynamics. Intracranial aneurysms (IA) are lethal, with high morbidity and mortality rates. Reliable, rapid, and accurate segmentation of IAs and their adjacent vasculature from medical imaging data is important to improve the clinical management of patients with IAs. However, due to the blurred boundaries and complex structure of IAs and overlapping with brain tissue or other cerebral arteries, image segmentation of IAs remains challenging. This study aimed to develop an attention residual U-Net (ARU-Net) architecture with differential preprocessing and geometric postprocessing for automatic segmentation of IAs and their adjacent arteries in conjunction with 3D rotational angiography (3DRA) images. The proposed ARU-Net followed the classic U-Net framework with the following key enhancements. First, we preprocessed the 3DRA images based on boundary enhancement to capture more contour information and enhance the presence of small vessels. Second, we introduced the long skip connections of the attention gate at each layer of the fully convolutional decoder-encoder structure to emphasize the field of view (FOV) for IAs. Third, residual-based short skip connections were also embedded in each layer to implement in-depth supervision to help the network converge. Fourth, we devised a multiscale supervision strategy for independent prediction at different levels of the decoding path, integrating multiscale semantic information to facilitate the segmentation of small vessels. Fifth, the 3D conditional random field (3DCRF) and 3D connected component optimization (3DCCO) were exploited as postprocessing to optimize the segmentation results. Comprehensive experimental assessments validated the effectiveness of our ARU-Net. The proposed ARU-Net model achieved comparable or superior performance to the state-of-the-art methods through quantitative and qualitative evaluations. Notably, we found that ARU-Net improved the identification of arteries connecting to an IA, including small arteries that were hard to recognize by other methods. Consequently, IA geometries segmented by the proposed ARU-Net model yielded superior performance during subsequent computational hemodynamic studies (also known as "patient-specific" computational fluid dynamics [CFD] simulations). Furthermore, in an ablation study, the five key enhancements mentioned above were confirmed. The proposed ARU-Net model can automatically segment the IAs in 3DRA images with relatively high accuracy and potentially has significant value for clinical computational hemodynamic analysis. [Display omitted]
ArticleNumber 102697
Author Tang, Jinshan
Jiang, Jingfeng
Lyu, Zonghan
Mu, Nan
Rezaeitaleshmahalleh, Mostafa
AuthorAffiliation c Center for Biocomputing and Digital Health, Health Research Institute and Institute of Computing and Cybernetics, Michigan Technological University, Houghton, Michigan, USA
a Biomedical Engineering, Michigan Technological University, Houghton, Michigan USA
b Department of Health Administration and Policy, George Mason University, Fairfax, Virginia, USA
AuthorAffiliation_xml – name: c Center for Biocomputing and Digital Health, Health Research Institute and Institute of Computing and Cybernetics, Michigan Technological University, Houghton, Michigan, USA
– name: b Department of Health Administration and Policy, George Mason University, Fairfax, Virginia, USA
– name: a Biomedical Engineering, Michigan Technological University, Houghton, Michigan USA
Author_xml – sequence: 1
  givenname: Nan
  orcidid: 0000-0003-0476-7500
  surname: Mu
  fullname: Mu, Nan
  organization: Biomedical Engineering, Michigan Technological University, Houghton, MI United States
– sequence: 2
  givenname: Zonghan
  surname: Lyu
  fullname: Lyu, Zonghan
  organization: Biomedical Engineering, Michigan Technological University, Houghton, MI United States
– sequence: 3
  givenname: Mostafa
  surname: Rezaeitaleshmahalleh
  fullname: Rezaeitaleshmahalleh, Mostafa
  organization: Biomedical Engineering, Michigan Technological University, Houghton, MI United States
– sequence: 4
  givenname: Jinshan
  orcidid: 0000-0001-7266-8534
  surname: Tang
  fullname: Tang, Jinshan
  organization: Department of Health Administration and Policy, George Mason University, Fairfax, Virginia, United States
– sequence: 5
  givenname: Jingfeng
  orcidid: 0000-0001-8812-6246
  surname: Jiang
  fullname: Jiang, Jingfeng
  email: jjiang1@mtu.edu
  organization: Biomedical Engineering, Michigan Technological University, Houghton, MI United States
BackLink https://www.ncbi.nlm.nih.gov/pubmed/36462374$$D View this record in MEDLINE/PubMed
BookMark eNp9Uk1v3CAQRVWqJtn2F1SqOPbiLQYb25VaKYr6EWmlXNIzwjDeZWWDC3ij_Jn-1kI3SZseAgfQzHtvYOadoxPrLCD0tiTrkpT8w349gTZyTQmlKUJ517xAZyXjZdFWlJ083sv6FJ2HsCeENFVFXqFTxitOWVOdoV8XFssYwUbjLPYQjF7kiJfCQsS3Ju6wNsMAPgNSfPYwe6cgBGO3WFqNt-AmiN4oPLsQ_yY_4g1IbzNs525xdDjAdkoy-CCDWkYZFw_YWDUuOoOMjV4qL20uIy0s_i5M4TV6OcgxwJv7c4V-fP1yc_m92Fx_u7q82BSqqrtY9IQ3WvcKOl33UGsl245JymjftCoFeKvqAfhAe8nTrkjTtkpRwksCjFWErdDno-689KmrCvJrRjF7M0l_J5w04mnGmp3YuoPoWkbqLgu8vxfw7ucCIYrJBAXjmL7iliBoU3HWsbxW6N2_tR6LPAwlAbojQHkXgodBKBNlHlAqbUZREpENIPbijwFENoA4GiBx2X_cB_nnWZ-OLEg9PhjwIigDViWgBxWFduZZ_m9t5NGN
CitedBy_id crossref_primary_10_1007_s11517_025_03345_7
crossref_primary_10_1088_2057_1976_acf3ed
crossref_primary_10_1007_s00371_024_03730_7
crossref_primary_10_1016_j_compbiomed_2023_107648
crossref_primary_10_1109_ACCESS_2025_3552588
crossref_primary_10_1109_TASE_2025_3585728
crossref_primary_10_1186_s13244_024_01657_0
crossref_primary_10_1038_s41598_024_80891_4
crossref_primary_10_3390_bioengineering12050437
crossref_primary_10_1016_j_knosys_2025_113778
crossref_primary_10_1038_s41598_024_60475_y
crossref_primary_10_1007_s12530_023_09489_x
crossref_primary_10_3390_bioengineering12050552
crossref_primary_10_1007_s12194_025_00938_7
crossref_primary_10_1016_j_compmedimag_2024_102421
crossref_primary_10_1111_exsy_13588
crossref_primary_10_1186_s41016_023_00339_y
crossref_primary_10_1016_j_medengphy_2024_104244
crossref_primary_10_1016_j_nbd_2025_106877
crossref_primary_10_1016_j_compbiomed_2025_110370
crossref_primary_10_1186_s12880_024_01347_9
crossref_primary_10_1016_j_bspc_2025_108028
crossref_primary_10_1109_TCE_2025_3526801
crossref_primary_10_1016_j_engappai_2025_110794
crossref_primary_10_1016_j_compbiomed_2024_108838
crossref_primary_10_1007_s11220_024_00493_2
crossref_primary_10_1109_TIM_2024_3497186
crossref_primary_10_1016_j_displa_2024_102929
crossref_primary_10_1016_j_wneu_2024_10_108
crossref_primary_10_3390_medicina61040561
crossref_primary_10_3233_XST_240093
crossref_primary_10_1186_s12911_024_02585_1
crossref_primary_10_1007_s10044_024_01266_z
crossref_primary_10_1109_JBHI_2024_3448459
crossref_primary_10_1002_mp_70017
crossref_primary_10_3390_electronics12122750
crossref_primary_10_1002_ima_70071
crossref_primary_10_1016_j_tranon_2023_101833
crossref_primary_10_4274_TJAR_2023_231260
crossref_primary_10_1016_j_neucom_2025_129459
crossref_primary_10_1016_j_bspc_2023_105614
crossref_primary_10_1007_s11042_023_17652_4
crossref_primary_10_1016_j_nic_2025_05_002
crossref_primary_10_1007_s00701_024_06404_4
crossref_primary_10_1109_ACCESS_2023_3335045
crossref_primary_10_1148_ryai_240017
crossref_primary_10_1016_j_compbiomed_2024_108370
crossref_primary_10_1038_s41598_023_50989_2
crossref_primary_10_1002_ima_23199
crossref_primary_10_3389_fphys_2023_1209659
crossref_primary_10_1007_s12265_022_10352_8
crossref_primary_10_1007_s10439_025_03686_2
crossref_primary_10_1016_j_compbiomed_2024_108615
crossref_primary_10_1016_j_procs_2024_11_019
crossref_primary_10_3390_bioengineering10060722
crossref_primary_10_1136_jnis_2024_022784
crossref_primary_10_1016_j_knosys_2025_114359
crossref_primary_10_1007_s12265_025_10677_0
crossref_primary_10_1016_j_eswa_2025_128775
crossref_primary_10_1109_ACCESS_2025_3533417
Cites_doi 10.1016/j.jbiomech.2013.12.035
10.1177/0271678X19854640
10.1227/01.NEU.0000316847.64140.81
10.1038/s41592-020-01008-z
10.1148/radiol.2020192154
10.1136/neurintsurg-2019-015422
10.1109/TMI.2009.2021652
10.1186/s12880-020-00543-7
10.1007/s10439-015-1363-y
10.3174/ajnr.A2419
10.1002/jmri.25842
10.1109/TMI.2017.2695227
10.1007/s10278-018-0162-z
10.1038/35058500
10.1109/TMI.2020.2996645
10.1016/j.patcog.2021.108168
10.1007/s11517-008-0420-1
10.1007/s00701-020-04616-y
10.1117/12.2549761
10.3174/ajnr.A3558
10.1038/jcbfm.2009.176
10.1038/s41598-020-78384-1
10.1016/j.media.2016.10.004
10.1136/neurintsurg-2020-015824
10.1148/radiol.2018182225
10.1146/annurev.neuro.23.1.315
10.1002/jcp.30569
ContentType Journal Article
Copyright 2022 The Authors
Copyright © 2022 The Authors. Published by Elsevier B.V. All rights reserved.
Copyright_xml – notice: 2022 The Authors
– notice: Copyright © 2022 The Authors. Published by Elsevier B.V. All rights reserved.
DBID 6I.
AAFTH
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
5PM
DOI 10.1016/j.media.2022.102697
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE

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
Engineering
EISSN 1361-8423
EndPage 102697
ExternalDocumentID PMC9830590
36462374
10_1016_j_media_2022_102697
S1361841522003255
Genre Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: NIBIB NIH HHS
  grantid: R01 EB029570
GroupedDBID ---
--K
--M
.~1
0R~
1B1
1~.
1~5
29M
4.4
457
4G.
53G
5GY
5VS
6I.
7-5
71M
8P~
AACTN
AAEDT
AAEDW
AAFTH
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABBQC
ABJNI
ABLVK
ABMAC
ABMZM
ABXDB
ABYKQ
ACDAQ
ACGFS
ACIUM
ACIWK
ACNNM
ACPRK
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFRAH
AFTJW
AFXIZ
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
AJRQY
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ANZVX
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
BNPGV
C45
CAG
COF
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HVGLF
HX~
HZ~
IHE
J1W
JJJVA
KOM
LCYCR
M41
MO0
N9A
O-L
O9-
OAUVE
OVD
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SDF
SDG
SDP
SEL
SES
SEW
SPC
SPCBC
SSH
SST
SSV
SSZ
T5K
TEORI
UHS
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACIEU
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
ADVLN
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
CGR
CUY
CVF
ECM
EIF
NPM
7X8
5PM
ID FETCH-LOGICAL-c459t-b067ddbce9d5be5dca893a232b78cbe568c5fe6f2ba6a6a40788cc20610e33403
ISICitedReferencesCount 66
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000913159100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1361-8415
1361-8423
IngestDate Tue Sep 30 17:10:07 EDT 2025
Sun Nov 09 11:10:52 EST 2025
Thu Apr 03 07:01:16 EDT 2025
Sat Nov 29 07:00:45 EST 2025
Tue Nov 18 22:37:54 EST 2025
Fri Feb 23 02:38:03 EST 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Conditional random field
3D segmentation
Multiscale supervision
Depth-aware attention gate
Intracranial aneurysm
Language English
License This is an open access article under the CC BY-NC-ND license.
Copyright © 2022 The Authors. Published by Elsevier B.V. All rights reserved.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c459t-b067ddbce9d5be5dca893a232b78cbe568c5fe6f2ba6a6a40788cc20610e33403
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0003-0476-7500
0000-0001-7266-8534
0000-0001-8812-6246
OpenAccessLink https://dx.doi.org/10.1016/j.media.2022.102697
PMID 36462374
PQID 2746393333
PQPubID 23479
PageCount 1
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_9830590
proquest_miscellaneous_2746393333
pubmed_primary_36462374
crossref_citationtrail_10_1016_j_media_2022_102697
crossref_primary_10_1016_j_media_2022_102697
elsevier_sciencedirect_doi_10_1016_j_media_2022_102697
PublicationCentury 2000
PublicationDate 2023-02-01
PublicationDateYYYYMMDD 2023-02-01
PublicationDate_xml – month: 02
  year: 2023
  text: 2023-02-01
  day: 01
PublicationDecade 2020
PublicationPlace Netherlands
PublicationPlace_xml – name: Netherlands
PublicationTitle Medical image analysis
PublicationTitleAlternate Med Image Anal
PublicationYear 2023
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Gwilliam, Hoggard, Capener, Singh, Marzo, Verma, Wilkinson (bib0057) 2009; 29
O. Oktay, J. Schlemper, L.L. Folgoc, M. Lee, M. Heinrich, K. Misawa, K. Mori, S. McDonagh, N.Y. Hammerla, B. Kainz, B. Glocker, and D. Rueckert, “Attention u-net: learning where to look for the pancreas,” arXiv preprint
Jin, Geng, Yin, Hu, Yang, Xiang, Zhai, Ji, Fan, Hu, He, Qin, Zhang (bib0026) 2020; 12
Hatamizadeh, Terzopoulos, Myronenko (bib0049) 2019
Cebral, Mut, Weir, Putman (bib0003) 2011; 32
Mu, Wang, Zhang, Jiang, Tang (bib0052) 2021; 120
Meng, Tutino, Xiang, Siddiqui (bib0004) 2014; 35
Müller, Kramer (bib0017) 2021; 21
Xiang, Antiga, Varble, Snyder, Levy, Siddiqui, Meng (bib0007) 2016; 44
Valanarasu, Oza, Hacihaliloglu, Patel (bib0036) 2021
Fu, Liu, Tian, Li, Bao, Fang, Lu (bib0033) 2019
Isensee, Jaeger, Kohl, Petersen, Maier-Hein (bib0011) 2021; 18
Seferbekov, Iglovikov, Buslaev, Shvets (bib0040) 2018
Cheng, Xiao, Yuan, Wang (bib0029) 2021
Çiçek, Abdulkadir, Lienkamp, Brox, Ronneberger (bib0010) 2016
Milletari, Navab, Ahmadi (bib0046) 2016
Saqr, Rashad, Tupin, Niizuma, Hassan, Tominaga, Ohta (bib0001) 2020; 40
Shahzad, Pennig, Goertz, Thiele, Kabbasch, Schlamann, Krischek, Maintz, Perkuhn, Borggrefe (bib0028) 2020; 10
Bello, Zoph, Vaswani, Shlens, Le (bib0032) 2019
He, Zhang, Ren, Sun (bib0037) 2015
Fan, Zhou, Ji, Zhou, Chen, Fu, Shen, Shao (bib0051) 2020; 39
Flanders (bib0022) 2019; 290
Salehi, Erdogmus, Gholipour (bib0042) 2017
Stember, Chang, Stember, Liu, Grinband, Filippi, Meyers, Jambawalikar (bib0025) 2019; 32
Damiano, Tutino, Paliwal, Patel, Waqas, Levy, Davies, Siddiqui, Meng (bib0006) 2020; 12
Krähenbühl, Koltun (bib0043) 2011
pp. 1–10, 2022.
pp. 1–10, 2018.
He, Zhang, Ren, Sun (bib0014) 2016
Kong, Sun, Wu, Liu, Lin (bib0041) 2018
Antiga, Piccinelli, Botti, Ene-Iordache, Remuzzi, Steinman (bib0002) 2008; 46
Yang, Xie, Hu, Alwalid, Xu, Liu, Jin, Li, Tu, Liu, Zhang, Li, Long (bib0009) 2021; 298
Mnih, Heess, Graves, kavukcuoglu (bib0031) 2014
Wang, Zhu, Green, Adam, Yuille, Chen (bib0054) 2020
Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (bib0053) 2017
Valanarasu, Sindagi, Hacihaliloglu, Patel (bib0018) 2021
Bhalerao, Thakur (bib0016) 2019
Wong, Moradi, Tang, Syeda-Mahmood (bib0045) 2018
Sunderland, Wang, Pandey, Gemmete, Huang, Goudge, Jiang (bib0055) 2021; 163
Nakao, Hanaoka, Nomura, Sato, Nemoto, Miki, Maeda, Yoshikawa, Hayashi, Abe (bib0024) 2018; 47
Dhar, Tremmel, Mocco, Kim, Yamamoto, Siddiqui, Hopkins, Meng (bib0005) 2008; 63
Piccinelli, Veneziani, Steinman, Remuzzi, Antiga (bib0019) 2009; 28
Qin, Zhang, Huang, Gao, Dehghan, Jagersand (bib0050) 2019
Sunderland, Jiang, Zhao (bib0044) 2022; 237
D. Shao, X. Lu, and X. Liu, “3D intracranial aneurysm classification and segmentation via unsupervised Dual-branch learning,” arXiv preprint
Brosch, Yoo, Tang, Li, Traboulsee, Tam (bib0048) 2015
Patel, Paliwal, Jaiswal, Waqas, Mokin, Siddiqui, Meng, Rai, Tutino (bib0027) 2020; 2020
Kamnitsas, Ledig, Newcombe, Simpson, Kane, Menon (bib0015) 2017; 36
Kastner, Ungerleider (bib0012) 2000; 23
Sunderland, Haferman, Chintalapani, Jiang (bib0056) 2016; 2016
Jirik, Lukes, Svobodova, Zelezny (bib0020) 2013
Lin, Dollar, Girshick, He, Hariharan, Belongie (bib0039) 2017
Yuan, Chao, Lo (bib0047) 2017; 36
Itti, Koch (bib0013) 2001; 2
Dosovitskiy, Beyer, Kolesnikov, Weissenborn, Zhai, Unterthiner, Dehghani, Minderer, Heigold, Gelly, Uszkoreit, Houlsby (bib0034) 2021
Ronneberger, Fischer, Brox (bib0008) 2015
Liu, Lin, Cao, Hu, Wei, Zhang, Lin, Guo (bib0035) 2021
Sen, Qian, Avolio, Morgan (bib0021) 2014; 47
Qin (10.1016/j.media.2022.102697_bib0050) 2019
Salehi (10.1016/j.media.2022.102697_bib0042) 2017
Mu (10.1016/j.media.2022.102697_bib0052) 2021; 120
Stember (10.1016/j.media.2022.102697_bib0025) 2019; 32
Kong (10.1016/j.media.2022.102697_bib0041) 2018
Yuan (10.1016/j.media.2022.102697_bib0047) 2017; 36
Meng (10.1016/j.media.2022.102697_bib0004) 2014; 35
He (10.1016/j.media.2022.102697_bib0014) 2016
Isensee (10.1016/j.media.2022.102697_bib0011) 2021; 18
Sunderland (10.1016/j.media.2022.102697_bib0056) 2016; 2016
Lin (10.1016/j.media.2022.102697_bib0039) 2017
Dhar (10.1016/j.media.2022.102697_bib0005) 2008; 63
Müller (10.1016/j.media.2022.102697_bib0017) 2021; 21
He (10.1016/j.media.2022.102697_bib0037) 2015
Bhalerao (10.1016/j.media.2022.102697_bib0016) 2019
Sunderland (10.1016/j.media.2022.102697_bib0055) 2021; 163
Flanders (10.1016/j.media.2022.102697_bib0022) 2019; 290
Valanarasu (10.1016/j.media.2022.102697_bib0018) 2021
Sunderland (10.1016/j.media.2022.102697_bib0044) 2022; 237
Jin (10.1016/j.media.2022.102697_bib0026) 2020; 12
Bello (10.1016/j.media.2022.102697_bib0032) 2019
Seferbekov (10.1016/j.media.2022.102697_bib0040) 2018
Piccinelli (10.1016/j.media.2022.102697_bib0019) 2009; 28
Itti (10.1016/j.media.2022.102697_bib0013) 2001; 2
Jirik (10.1016/j.media.2022.102697_bib0020) 2013
Yang (10.1016/j.media.2022.102697_bib0009) 2021; 298
Cheng (10.1016/j.media.2022.102697_bib0029) 2021
Liu (10.1016/j.media.2022.102697_bib0035) 2021
Antiga (10.1016/j.media.2022.102697_bib0002) 2008; 46
Nakao (10.1016/j.media.2022.102697_bib0024) 2018; 47
Wang (10.1016/j.media.2022.102697_bib0054) 2020
Gwilliam (10.1016/j.media.2022.102697_bib0057) 2009; 29
Milletari (10.1016/j.media.2022.102697_bib0046) 2016
Shahzad (10.1016/j.media.2022.102697_bib0028) 2020; 10
Çiçek (10.1016/j.media.2022.102697_bib0010) 2016
Sen (10.1016/j.media.2022.102697_bib0021) 2014; 47
Wong (10.1016/j.media.2022.102697_bib0045) 2018
Dosovitskiy (10.1016/j.media.2022.102697_bib0034) 2021
Kamnitsas (10.1016/j.media.2022.102697_bib0015) 2017; 36
Hatamizadeh (10.1016/j.media.2022.102697_bib0049) 2019
Ronneberger (10.1016/j.media.2022.102697_bib0008) 2015
Saqr (10.1016/j.media.2022.102697_bib0001) 2020; 40
10.1016/j.media.2022.102697_bib0030
Patel (10.1016/j.media.2022.102697_bib0027) 2020; 2020
Damiano (10.1016/j.media.2022.102697_bib0006) 2020; 12
Valanarasu (10.1016/j.media.2022.102697_bib0036) 2021
Vaswani (10.1016/j.media.2022.102697_bib0053) 2017
10.1016/j.media.2022.102697_bib0038
Xiang (10.1016/j.media.2022.102697_bib0007) 2016; 44
Mnih (10.1016/j.media.2022.102697_bib0031) 2014
Fu (10.1016/j.media.2022.102697_bib0033) 2019
Brosch (10.1016/j.media.2022.102697_bib0048) 2015
Cebral (10.1016/j.media.2022.102697_bib0003) 2011; 32
Kastner (10.1016/j.media.2022.102697_bib0012) 2000; 23
Krähenbühl (10.1016/j.media.2022.102697_bib0043) 2011
Fan (10.1016/j.media.2022.102697_bib0051) 2020; 39
References_xml – volume: 36
  start-page: 61
  year: 2017
  end-page: 78
  ident: bib0015
  article-title: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
  publication-title: Med. Image Anal.
– volume: 290
  start-page: 195
  year: 2019
  end-page: 197
  ident: bib0022
  article-title: Machine learning detection of intracranial aneurysms—Will it play in Peoria?
  publication-title: Radiology
– start-page: 7479
  year: 2019
  end-page: 7489
  ident: bib0050
  article-title: Basnet: boundary-aware salient object detection
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– volume: 2
  start-page: 194
  year: 2001
  end-page: 203
  ident: bib0013
  article-title: Computational modelling of visual attention
  publication-title: Nat. Rev. Neurosci.
– start-page: 108
  year: 2020
  end-page: 126
  ident: bib0054
  article-title: Axial-deeplab: stand-alone axial-attention for panoptic segmentation
  publication-title: European Conference on Computer Vision
– start-page: 612
  year: 2018
  end-page: 619
  ident: bib0045
  article-title: 3D segmentation with exponential logarithmic loss for highly unbalanced object sizes
  publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention
– volume: 163
  start-page: 2339
  year: 2021
  end-page: 2349
  ident: bib0055
  article-title: Quantitative analysis of flow vortices: differentiation of unruptured and ruptured medium-sized middle cerebral artery aneurysms
  publication-title: Acta Neurochir (Wien)
– start-page: 218
  year: 2019
  end-page: 225
  ident: bib0016
  article-title: Brain tumor segmentation based on 3D residual U-Net
  publication-title: International MICCAI Brainlesion Workshop
– volume: 120
  start-page: 1
  year: 2021
  end-page: 12
  ident: bib0052
  article-title: Progressive global perception and local polishing network for lung infection segmentation of COVID-19 CT images
  publication-title: Pattern Recognit.
– volume: 46
  start-page: 1097
  year: 2008
  end-page: 1112
  ident: bib0002
  article-title: An image-based modeling framework for patient-specific computational hemodynamics
  publication-title: Med. Biol. Eng. Comput. Vol.
– volume: 63
  start-page: 185
  year: 2008
  end-page: 197
  ident: bib0005
  article-title: Morphology parameters for intracranial aneurysm rupture risk assessment
  publication-title: Neurosurgery
– volume: 237
  start-page: 278
  year: 2022
  end-page: 300
  ident: bib0044
  article-title: Disturbed flow's impact on cellular changes indicative of vascular aneurysm initiation, expansion, and rupture: a pathological and methodological review
  publication-title: J. Cell. Physiol.
– volume: 18
  start-page: 203
  year: 2021
  end-page: 211
  ident: bib0011
  article-title: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
  publication-title: Nat. Methods
– start-page: 565
  year: 2016
  end-page: 571
  ident: bib0046
  article-title: V-net: fully convolutional neural networks for volumetric medical image segmentation
  publication-title: 2016 fourth international conference on 3D vision
– volume: 44
  start-page: 1085
  year: 2016
  end-page: 1096
  ident: bib0007
  article-title: AView: an image-based clinical computational tool for intracranial aneurysm flow visualization and clinical management
  publication-title: Ann. Biomed. Eng.
– reference: O. Oktay, J. Schlemper, L.L. Folgoc, M. Lee, M. Heinrich, K. Misawa, K. Mori, S. McDonagh, N.Y. Hammerla, B. Kainz, B. Glocker, and D. Rueckert, “Attention u-net: learning where to look for the pancreas,” arXiv preprint
– volume: 2016
  year: 2016
  ident: bib0056
  article-title: Vortex analysis of intra-aneurismal flow in cerebral aneurysms
  publication-title: Comput. Math. Methods Med.
– start-page: 770
  year: 2016
  end-page: 778
  ident: bib0014
  article-title: Deep residual learning for image recognition
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– volume: 10
  start-page: 1
  year: 2020
  end-page: 12
  ident: bib0028
  article-title: Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning
  publication-title: Sci. Rep.
– start-page: 2117
  year: 2017
  end-page: 2125
  ident: bib0039
  article-title: Feature pyramid networks for object detection
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 3286
  year: 2019
  end-page: 3295
  ident: bib0032
  article-title: Attention augmented convolutional networks
  publication-title: IEEE International Conference on Computer Vision
– volume: 36
  start-page: 1876
  year: 2017
  end-page: 1886
  ident: bib0047
  article-title: Automatic skin lesion segmentation using deep fully convolutional networks with jaccard distance
  publication-title: IEEE Trans. Med. Imag.
– start-page: 187
  year: 2019
  end-page: 194
  ident: bib0049
  article-title: End-to-end boundary aware networks for medical image segmentation
  publication-title: International Workshop on Machine Learning in Medical Imaging
– start-page: 1
  year: 2021
  end-page: 13
  ident: bib0018
  article-title: KiU-Net: overcomplete convolutional architectures for biomedical image and volumetric segmentation
  publication-title: IEEE Trans. Med. Imag.
– start-page: 236
  year: 2021
  end-page: 241
  ident: bib0029
  article-title: Automatic intracranial aneurysm segmentation based on spatial information fusion feature from 3D-RA using U-Net
  publication-title: IEEE International Conference on Mechatronics and Automation
– volume: 40
  start-page: 1021
  year: 2020
  end-page: 1039
  ident: bib0001
  article-title: What does computational fluid dynamics tell us about intracranial aneurysms? A meta-analysis and critical review
  publication-title: J. Cereb. Blood Flow Metabol.
– reference: D. Shao, X. Lu, and X. Liu, “3D intracranial aneurysm classification and segmentation via unsupervised Dual-branch learning,” arXiv preprint
– start-page: 109
  year: 2011
  end-page: 117
  ident: bib0043
  article-title: Efficient inference in fully connected CRFs with gaussian edge potentials
  publication-title: Advances in Neural Information Processing Systems
– volume: 298
  start-page: 155
  year: 2021
  end-page: 163
  ident: bib0009
  article-title: Deep learning for detecting cerebral aneurysms with CT angiography
  publication-title: Radiology
– volume: 32
  start-page: 808
  year: 2019
  end-page: 815
  ident: bib0025
  article-title: Convolutional neural networks for the detection and measurement of cerebral aneurysms on magnetic resonance angiography
  publication-title: J. Digit. Imag.
– volume: 12
  start-page: 1023
  year: 2020
  end-page: 1027
  ident: bib0026
  article-title: Fully automated intracranial aneurysm detection and segmentation from digital subtraction angiography series using an end-to-end spatiotemporal deep neural network
  publication-title: J. Neurointerv. Surg.
– start-page: 379
  year: 2017
  end-page: 387
  ident: bib0042
  article-title: Tversky loss function for image segmentation using 3D fully convolutional deep networks
  publication-title: International Workshop on Machine Learning in Medical Imaging
– start-page: 234
  year: 2015
  end-page: 241
  ident: bib0008
  article-title: U-net: convolutional networks for biomedical image segmentation
  publication-title: Med. Image Comput. Comp.-Assist. Intervent.
– volume: 23
  start-page: 315
  year: 2000
  end-page: 341
  ident: bib0012
  article-title: Mechanisms of visual attention in the human cortex
  publication-title: Annu. Rev. Neurosci.
– volume: 47
  start-page: 1014
  year: 2014
  end-page: 1019
  ident: bib0021
  article-title: Image segmentation methods for intracranial aneurysm haemodynamic research
  publication-title: J. Biomech.
– volume: 39
  start-page: 2626
  year: 2020
  end-page: 2637
  ident: bib0051
  article-title: Inf-net: automatic covid-19 lung infection segmentation from ct images
  publication-title: IEEE Trans. Med. Imag.
– volume: 32
  start-page: 145
  year: 2011
  end-page: 151
  ident: bib0003
  article-title: Quantitative characterization of the hemodynamic environment in ruptured and unruptured brain aneurysms
  publication-title: Am. J. Neuroradiol.
– start-page: 346
  year: 2018
  end-page: 355
  ident: bib0041
  article-title: Hybrid pyramid u-net model for brain tumor segmentation
  publication-title: International Conference on Intelligent Information Processing
– start-page: 272
  year: 2018
  end-page: 275
  ident: bib0040
  article-title: Feature pyramid network for multi-class land segmentation
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 3
  year: 2015
  end-page: 11
  ident: bib0048
  article-title: Deep convolutional encoder networks for multiple sclerosis lesion segmentation
  publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention
– start-page: 424
  year: 2016
  end-page: 432
  ident: bib0010
  article-title: 3D U-Net: learning dense volumetric segmentation from sparse annotation
  publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention
– start-page: 1
  year: 2021
  end-page: 22
  ident: bib0034
  article-title: An image is worth 16x16 words: transformers for image recognition at scale
  publication-title: International Conference on Learning Representations
– volume: 29
  start-page: 1975
  year: 2009
  end-page: 1982
  ident: bib0057
  article-title: MR derived volumetric flow rate waveforms at locations within the common carotid, internal carotid, and basilar arteries
  publication-title: J. Cereb. Blood Flow Metabol.
– reference: , pp. 1–10, 2022.
– volume: 35
  start-page: 1254
  year: 2014
  end-page: 1262
  ident: bib0004
  article-title: High WSS or low WSS? Complex interactions of hemodynamics with intracranial aneurysm initiation, growth, and rupture: toward a unifying hypothesis
  publication-title: Am. J. Neuroradiol.
– volume: 12
  start-page: 706
  year: 2020
  end-page: 713
  ident: bib0006
  article-title: Aneurysm characteristics, coil packing, and post-coiling hemodynamics affect long-term treatment outcome
  publication-title: J. Neurointerv. Surg.
– volume: 47
  start-page: 948
  year: 2018
  end-page: 953
  ident: bib0024
  article-title: Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography
  publication-title: J. Magnet. Reson. Imag.
– volume: 21
  start-page: 1
  year: 2021
  end-page: 11
  ident: bib0017
  article-title: MIScnn: a framework for medical image segmentation with convolutional neural networks and deep learning
  publication-title: BMC Med. Imag.
– start-page: 1
  year: 2014
  end-page: 9
  ident: bib0031
  article-title: Recurrent models of visual attention
  publication-title: Advances in Neural Information Processing Systems
– start-page: 3146
  year: 2019
  end-page: 3154
  ident: bib0033
  article-title: Dual attention network for scene segmentation
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 10012
  year: 2021
  end-page: 10022
  ident: bib0035
  article-title: Swin transformer: hierarchical vision transformer using shifted windows
  publication-title: IEEE International Conference on Computer Vision
– start-page: 1026
  year: 2015
  end-page: 1034
  ident: bib0037
  article-title: Delving deep into rectifiers: surpassing human-level performance on imagenet classification
  publication-title: IEEE International Conference on Computer Vision
– start-page: 201
  year: 2013
  end-page: 204
  ident: bib0020
  article-title: Image segmentation in medical imaging via graph-cuts
  publication-title: 11th International Conference on Pattern Recognition and Image Analysis: New Information Technologies
– start-page: 36
  year: 2021
  end-page: 46
  ident: bib0036
  article-title: Medical transformer: gated axial-attention for medical image segmentation
  publication-title: Medical Image Computing and Computer Assisted Intervention
– volume: 28
  start-page: 1141
  year: 2009
  end-page: 1155
  ident: bib0019
  article-title: A framework for geometric analysis of vascular structures: application to cerebral aneurysms
  publication-title: IEEE Trans. Med. Imag.
– reference: , pp. 1–10, 2018.
– start-page: 1
  year: 2017
  end-page: 11
  ident: bib0053
  article-title: Attention is all you need
  publication-title: 31st Conference on Neural Information Processing Systems
– volume: 2020
  year: 2020
  ident: bib0027
  article-title: Multi-resolution CNN for brain vessel segmentation from cerebrovascular images of intracranial aneurysm: a comparison of U-Net and DeepMedic
  publication-title: Comp.-Aid. Diagn.
– start-page: 187
  year: 2019
  ident: 10.1016/j.media.2022.102697_bib0049
  article-title: End-to-end boundary aware networks for medical image segmentation
– volume: 47
  start-page: 1014
  issue: 5
  year: 2014
  ident: 10.1016/j.media.2022.102697_bib0021
  article-title: Image segmentation methods for intracranial aneurysm haemodynamic research
  publication-title: J. Biomech.
  doi: 10.1016/j.jbiomech.2013.12.035
– start-page: 218
  year: 2019
  ident: 10.1016/j.media.2022.102697_bib0016
  article-title: Brain tumor segmentation based on 3D residual U-Net
– volume: 40
  start-page: 1021
  issue: 5
  year: 2020
  ident: 10.1016/j.media.2022.102697_bib0001
  article-title: What does computational fluid dynamics tell us about intracranial aneurysms? A meta-analysis and critical review
  publication-title: J. Cereb. Blood Flow Metabol.
  doi: 10.1177/0271678X19854640
– volume: 63
  start-page: 185
  issue: 2
  year: 2008
  ident: 10.1016/j.media.2022.102697_bib0005
  article-title: Morphology parameters for intracranial aneurysm rupture risk assessment
  publication-title: Neurosurgery
  doi: 10.1227/01.NEU.0000316847.64140.81
– start-page: 1
  year: 2017
  ident: 10.1016/j.media.2022.102697_bib0053
  article-title: Attention is all you need
– start-page: 3146
  year: 2019
  ident: 10.1016/j.media.2022.102697_bib0033
  article-title: Dual attention network for scene segmentation
– volume: 18
  start-page: 203
  issue: 2
  year: 2021
  ident: 10.1016/j.media.2022.102697_bib0011
  article-title: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
  publication-title: Nat. Methods
  doi: 10.1038/s41592-020-01008-z
– start-page: 201
  year: 2013
  ident: 10.1016/j.media.2022.102697_bib0020
  article-title: Image segmentation in medical imaging via graph-cuts
– volume: 298
  start-page: 155
  issue: 1
  year: 2021
  ident: 10.1016/j.media.2022.102697_bib0009
  article-title: Deep learning for detecting cerebral aneurysms with CT angiography
  publication-title: Radiology
  doi: 10.1148/radiol.2020192154
– volume: 12
  start-page: 706
  issue: 7
  year: 2020
  ident: 10.1016/j.media.2022.102697_bib0006
  article-title: Aneurysm characteristics, coil packing, and post-coiling hemodynamics affect long-term treatment outcome
  publication-title: J. Neurointerv. Surg.
  doi: 10.1136/neurintsurg-2019-015422
– ident: 10.1016/j.media.2022.102697_bib0030
– start-page: 1
  year: 2014
  ident: 10.1016/j.media.2022.102697_bib0031
  article-title: Recurrent models of visual attention
– start-page: 379
  year: 2017
  ident: 10.1016/j.media.2022.102697_bib0042
  article-title: Tversky loss function for image segmentation using 3D fully convolutional deep networks
– start-page: 272
  year: 2018
  ident: 10.1016/j.media.2022.102697_bib0040
  article-title: Feature pyramid network for multi-class land segmentation
– volume: 2016
  issue: 1–17
  year: 2016
  ident: 10.1016/j.media.2022.102697_bib0056
  article-title: Vortex analysis of intra-aneurismal flow in cerebral aneurysms
  publication-title: Comput. Math. Methods Med.
– volume: 28
  start-page: 1141
  issue: 8
  year: 2009
  ident: 10.1016/j.media.2022.102697_bib0019
  article-title: A framework for geometric analysis of vascular structures: application to cerebral aneurysms
  publication-title: IEEE Trans. Med. Imag.
  doi: 10.1109/TMI.2009.2021652
– volume: 21
  start-page: 1
  issue: 1
  year: 2021
  ident: 10.1016/j.media.2022.102697_bib0017
  article-title: MIScnn: a framework for medical image segmentation with convolutional neural networks and deep learning
  publication-title: BMC Med. Imag.
  doi: 10.1186/s12880-020-00543-7
– volume: 44
  start-page: 1085
  issue: 4
  year: 2016
  ident: 10.1016/j.media.2022.102697_bib0007
  article-title: AView: an image-based clinical computational tool for intracranial aneurysm flow visualization and clinical management
  publication-title: Ann. Biomed. Eng.
  doi: 10.1007/s10439-015-1363-y
– volume: 32
  start-page: 145
  issue: 1
  year: 2011
  ident: 10.1016/j.media.2022.102697_bib0003
  article-title: Quantitative characterization of the hemodynamic environment in ruptured and unruptured brain aneurysms
  publication-title: Am. J. Neuroradiol.
  doi: 10.3174/ajnr.A2419
– ident: 10.1016/j.media.2022.102697_bib0038
– start-page: 612
  year: 2018
  ident: 10.1016/j.media.2022.102697_bib0045
  article-title: 3D segmentation with exponential logarithmic loss for highly unbalanced object sizes
– start-page: 108
  year: 2020
  ident: 10.1016/j.media.2022.102697_bib0054
  article-title: Axial-deeplab: stand-alone axial-attention for panoptic segmentation
– start-page: 36
  year: 2021
  ident: 10.1016/j.media.2022.102697_bib0036
  article-title: Medical transformer: gated axial-attention for medical image segmentation
– start-page: 3286
  year: 2019
  ident: 10.1016/j.media.2022.102697_bib0032
  article-title: Attention augmented convolutional networks
– start-page: 2117
  year: 2017
  ident: 10.1016/j.media.2022.102697_bib0039
  article-title: Feature pyramid networks for object detection
– volume: 47
  start-page: 948
  issue: 4
  year: 2018
  ident: 10.1016/j.media.2022.102697_bib0024
  article-title: Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography
  publication-title: J. Magnet. Reson. Imag.
  doi: 10.1002/jmri.25842
– volume: 36
  start-page: 1876
  issue: 9
  year: 2017
  ident: 10.1016/j.media.2022.102697_bib0047
  article-title: Automatic skin lesion segmentation using deep fully convolutional networks with jaccard distance
  publication-title: IEEE Trans. Med. Imag.
  doi: 10.1109/TMI.2017.2695227
– volume: 32
  start-page: 808
  year: 2019
  ident: 10.1016/j.media.2022.102697_bib0025
  article-title: Convolutional neural networks for the detection and measurement of cerebral aneurysms on magnetic resonance angiography
  publication-title: J. Digit. Imag.
  doi: 10.1007/s10278-018-0162-z
– start-page: 1026
  year: 2015
  ident: 10.1016/j.media.2022.102697_bib0037
  article-title: Delving deep into rectifiers: surpassing human-level performance on imagenet classification
– volume: 2
  start-page: 194
  issue: 3
  year: 2001
  ident: 10.1016/j.media.2022.102697_bib0013
  article-title: Computational modelling of visual attention
  publication-title: Nat. Rev. Neurosci.
  doi: 10.1038/35058500
– start-page: 770
  year: 2016
  ident: 10.1016/j.media.2022.102697_bib0014
  article-title: Deep residual learning for image recognition
– volume: 39
  start-page: 2626
  issue: 8
  year: 2020
  ident: 10.1016/j.media.2022.102697_bib0051
  article-title: Inf-net: automatic covid-19 lung infection segmentation from ct images
  publication-title: IEEE Trans. Med. Imag.
  doi: 10.1109/TMI.2020.2996645
– volume: 120
  start-page: 1
  year: 2021
  ident: 10.1016/j.media.2022.102697_bib0052
  article-title: Progressive global perception and local polishing network for lung infection segmentation of COVID-19 CT images
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2021.108168
– volume: 46
  start-page: 1097
  issue: 11
  year: 2008
  ident: 10.1016/j.media.2022.102697_bib0002
  article-title: An image-based modeling framework for patient-specific computational hemodynamics
  publication-title: Med. Biol. Eng. Comput. Vol.
  doi: 10.1007/s11517-008-0420-1
– start-page: 234
  year: 2015
  ident: 10.1016/j.media.2022.102697_bib0008
  article-title: U-net: convolutional networks for biomedical image segmentation
  publication-title: Med. Image Comput. Comp.-Assist. Intervent.
– start-page: 346
  year: 2018
  ident: 10.1016/j.media.2022.102697_bib0041
  article-title: Hybrid pyramid u-net model for brain tumor segmentation
– volume: 163
  start-page: 2339
  year: 2021
  ident: 10.1016/j.media.2022.102697_bib0055
  article-title: Quantitative analysis of flow vortices: differentiation of unruptured and ruptured medium-sized middle cerebral artery aneurysms
  publication-title: Acta Neurochir (Wien)
  doi: 10.1007/s00701-020-04616-y
– volume: 2020
  year: 2020
  ident: 10.1016/j.media.2022.102697_bib0027
  article-title: Multi-resolution CNN for brain vessel segmentation from cerebrovascular images of intracranial aneurysm: a comparison of U-Net and DeepMedic
  publication-title: Comp.-Aid. Diagn.
  doi: 10.1117/12.2549761
– volume: 35
  start-page: 1254
  issue: 7
  year: 2014
  ident: 10.1016/j.media.2022.102697_bib0004
  article-title: High WSS or low WSS? Complex interactions of hemodynamics with intracranial aneurysm initiation, growth, and rupture: toward a unifying hypothesis
  publication-title: Am. J. Neuroradiol.
  doi: 10.3174/ajnr.A3558
– start-page: 1
  year: 2021
  ident: 10.1016/j.media.2022.102697_bib0018
  article-title: KiU-Net: overcomplete convolutional architectures for biomedical image and volumetric segmentation
  publication-title: IEEE Trans. Med. Imag.
– start-page: 1
  year: 2021
  ident: 10.1016/j.media.2022.102697_bib0034
  article-title: An image is worth 16x16 words: transformers for image recognition at scale
– volume: 29
  start-page: 1975
  issue: 12
  year: 2009
  ident: 10.1016/j.media.2022.102697_bib0057
  article-title: MR derived volumetric flow rate waveforms at locations within the common carotid, internal carotid, and basilar arteries
  publication-title: J. Cereb. Blood Flow Metabol.
  doi: 10.1038/jcbfm.2009.176
– start-page: 10012
  year: 2021
  ident: 10.1016/j.media.2022.102697_bib0035
  article-title: Swin transformer: hierarchical vision transformer using shifted windows
– volume: 10
  start-page: 1
  issue: 1
  year: 2020
  ident: 10.1016/j.media.2022.102697_bib0028
  article-title: Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-020-78384-1
– volume: 36
  start-page: 61
  year: 2017
  ident: 10.1016/j.media.2022.102697_bib0015
  article-title: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2016.10.004
– start-page: 565
  year: 2016
  ident: 10.1016/j.media.2022.102697_bib0046
  article-title: V-net: fully convolutional neural networks for volumetric medical image segmentation
– start-page: 424
  year: 2016
  ident: 10.1016/j.media.2022.102697_bib0010
  article-title: 3D U-Net: learning dense volumetric segmentation from sparse annotation
– volume: 12
  start-page: 1023
  issue: 10
  year: 2020
  ident: 10.1016/j.media.2022.102697_bib0026
  article-title: Fully automated intracranial aneurysm detection and segmentation from digital subtraction angiography series using an end-to-end spatiotemporal deep neural network
  publication-title: J. Neurointerv. Surg.
  doi: 10.1136/neurintsurg-2020-015824
– volume: 290
  start-page: 195
  issue: 1
  year: 2019
  ident: 10.1016/j.media.2022.102697_bib0022
  article-title: Machine learning detection of intracranial aneurysms—Will it play in Peoria?
  publication-title: Radiology
  doi: 10.1148/radiol.2018182225
– volume: 23
  start-page: 315
  issue: 1
  year: 2000
  ident: 10.1016/j.media.2022.102697_bib0012
  article-title: Mechanisms of visual attention in the human cortex
  publication-title: Annu. Rev. Neurosci.
  doi: 10.1146/annurev.neuro.23.1.315
– start-page: 236
  year: 2021
  ident: 10.1016/j.media.2022.102697_bib0029
  article-title: Automatic intracranial aneurysm segmentation based on spatial information fusion feature from 3D-RA using U-Net
– start-page: 3
  year: 2015
  ident: 10.1016/j.media.2022.102697_bib0048
  article-title: Deep convolutional encoder networks for multiple sclerosis lesion segmentation
– start-page: 7479
  year: 2019
  ident: 10.1016/j.media.2022.102697_bib0050
  article-title: Basnet: boundary-aware salient object detection
– volume: 237
  start-page: 278
  issue: 1
  year: 2022
  ident: 10.1016/j.media.2022.102697_bib0044
  article-title: Disturbed flow's impact on cellular changes indicative of vascular aneurysm initiation, expansion, and rupture: a pathological and methodological review
  publication-title: J. Cell. Physiol.
  doi: 10.1002/jcp.30569
– start-page: 109
  year: 2011
  ident: 10.1016/j.media.2022.102697_bib0043
  article-title: Efficient inference in fully connected CRFs with gaussian edge potentials
SSID ssj0007440
Score 2.590035
Snippet •This paper proposes automatically segmenting vasculature, including intracranial aneurysms, from 3DRA images with the need for “patient-specific”...
Intracranial aneurysms (IA) are lethal, with high morbidity and mortality rates. Reliable, rapid, and accurate segmentation of IAs and their adjacent...
SourceID pubmedcentral
proquest
pubmed
crossref
elsevier
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 102697
SubjectTerms 3D segmentation
Angiography
Attention
Conditional random field
Depth-aware attention gate
Humans
Image Processing, Computer-Assisted - methods
Imaging, Three-Dimensional - methods
Intracranial aneurysm
Intracranial Aneurysm - diagnostic imaging
Multiscale supervision
Title An attention residual u-net with differential preprocessing and geometric postprocessing: Learning how to segment vasculature including intracranial aneurysms
URI https://dx.doi.org/10.1016/j.media.2022.102697
https://www.ncbi.nlm.nih.gov/pubmed/36462374
https://www.proquest.com/docview/2746393333
https://pubmed.ncbi.nlm.nih.gov/PMC9830590
Volume 84
WOSCitedRecordID wos000913159100002&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1361-8423
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0007440
  issn: 1361-8415
  databaseCode: AIEXJ
  dateStart: 20161201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLa6DSF4QDAYlMtkJN5KpjbOxeGtQkMwsQmhIlW8RKnjtplap2rSafBj-DX8MI6vTVdRsQdaKYqc2HJ7PtvHx985B6E3Wc8fZYTDSBv1ci-gY-4lIZfWpl7OQkoTPg5Uson44oIOh8mXVuu39YW5msVC0OvrZPFfRQ1lIGzpOnsLcbtGoQDuQehwBbHD9Z8E3xcdGTNTsxhhM629rVae4LW2utqcKLU0li9kVEvlK2C9FSe8nMs0W6yzKKt6_VDaDj5bQ8pUZqIrOxWfKDKB4bOq04hCsNnKuMrUy4zBYliogAQcxFeZ4Og2h5Q5JirmkjqUmQApaxCY-d-xhn6oku-lmEzXpV_5z4zL3Ce8ms4zlRxG2YrOofvZ2C07A2MZPytEZWsbc4dPLEPazdAk6nk00D6gdgqnQWMOBpUp0pzfreVBWyouT5RXzgk075-s394Mxn1jkXTURcuKu0xVI6lsJNWN7KEDPw4TmFsP-p9Oh2dOI5BBGLX_n-66jX6leIZbffmbhrS9A7pJ5G1oRoOH6IHZ0uC-huIj1OLiEN1vBLo8RHfPDYXjMfrVF9jhE1t8YoVPLPGJm_jEG_jEgE_s8Ik38fkOW3RiQCeuS2zQiRvoxA6duIlO7ND5BH37cDp4_9EzSUI8FoRJ7Y1A3crzEeNJHo54mLMMNPAM9gmjmDIoiKjkU0ZjmJIi-Mpja8qYD2pslxMSdMkR2hel4M8QzvJ43CV-RiLKg4AnCeV56POY0G4uk7i1kW8FkzITQV8mcpmlO0DRRm9dpYUOILP79chKPDU6sNZtU8Dw7oqvLT5SWCHksR_8deWqSv04gG0IgU8bPdV4cT0hUQD7nzhoo3gDSe4FGX1-84kopioKfUKJdFx_frvf9wLdW4_ql2i_Xq74K3SHXdVFtTxGe_GQHpvh8wepxwkh
linkProvider Elsevier
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=An+attention+residual+u-net+with+differential+preprocessing+and+geometric+postprocessing%3A+Learning+how+to+segment+vasculature+including+intracranial+aneurysms&rft.jtitle=Medical+image+analysis&rft.au=Mu%2C+Nan&rft.au=Lyu%2C+Zonghan&rft.au=Rezaeitaleshmahalleh%2C+Mostafa&rft.au=Tang%2C+Jinshan&rft.date=2023-02-01&rft.issn=1361-8415&rft.volume=84&rft.spage=102697&rft_id=info:doi/10.1016%2Fj.media.2022.102697&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_media_2022_102697
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1361-8415&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1361-8415&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1361-8415&client=summon