MIRAU-Net: An improved neural network based on U-Net for gliomas segmentation

Gliomas are the largest prevalent and destructive of brain tumors and have crucial parts for the diagnosing and treating of MRI brain tumors during segmentation using computerized methods. Recently, U-Net architecture has achieved impressive brain tumor segmentation, but this role remains challengin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Signal processing. Image communication Jg. 101; S. 116553
Hauptverfasser: AboElenein, Nagwa M., Piao, Songhao, Noor, Alam, Ahmed, Pir Noman
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier B.V 01.02.2022
Elsevier BV
Schlagworte:
ISSN:0923-5965, 1879-2677
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Gliomas are the largest prevalent and destructive of brain tumors and have crucial parts for the diagnosing and treating of MRI brain tumors during segmentation using computerized methods. Recently, U-Net architecture has achieved impressive brain tumor segmentation, but this role remains challenging due to the differing severity and appearance of gliomas. Therefore, we proposed a novel encoder–decoder architecture called Multi Inception Residual Attention U-Net (MIRAU-Net) in this work. It integrates residual inception modules with attention gates into U-Net to further enhance brain tumor segmentation performance. Encoder–decoder is connected in this architecture through Inception Residual pathways to decrease the distance between their maps of features. We use the weight cross-entropy and generalized Dice (GDL) with focal Tversky loss functions to resolve the class imbalance problem. The evaluation performance of MIRAU-Net checked with Brats 2019 and obtained mean dice similarities of 0.885 for the whole tumor, 0.879 for the core area, and 0.818 for the enhancement tumor. Experiment results reveal that the suggested MIRAU-Net beats its baselines and provides better efficiency than recent techniques for brain tumor segmentation. •A novel approach is proposed for brain tumor segmentation enhancement.•The proposed network combines Residual-Inception modules and Attention module with U-Net architecture.•The encoder and decoder are connected via a sequence of Inception-Res paths.•Apply the proposed network to Brats 2019.
AbstractList Gliomas are the largest prevalent and destructive of brain tumors and have crucial parts for the diagnosing and treating of MRI brain tumors during segmentation using computerized methods. Recently, U-Net architecture has achieved impressive brain tumor segmentation, but this role remains challenging due to the differing severity and appearance of gliomas. Therefore, we proposed a novel encoder–decoder architecture called Multi Inception Residual Attention U-Net (MIRAU-Net) in this work. It integrates residual inception modules with attention gates into U-Net to further enhance brain tumor segmentation performance. Encoder–decoder is connected in this architecture through Inception Residual pathways to decrease the distance between their maps of features. We use the weight cross-entropy and generalized Dice (GDL) with focal Tversky loss functions to resolve the class imbalance problem. The evaluation performance of MIRAU-Net checked with Brats 2019 and obtained mean dice similarities of 0.885 for the whole tumor, 0.879 for the core area, and 0.818 for the enhancement tumor. Experiment results reveal that the suggested MIRAU-Net beats its baselines and provides better efficiency than recent techniques for brain tumor segmentation. •A novel approach is proposed for brain tumor segmentation enhancement.•The proposed network combines Residual-Inception modules and Attention module with U-Net architecture.•The encoder and decoder are connected via a sequence of Inception-Res paths.•Apply the proposed network to Brats 2019.
Gliomas are the largest prevalent and destructive of brain tumors and have crucial parts for the diagnosing and treating of MRI brain tumors during segmentation using computerized methods. Recently, U-Net architecture has achieved impressive brain tumor segmentation, but this role remains challenging due to the differing severity and appearance of gliomas. Therefore, we proposed a novel encoder–decoder architecture called Multi Inception Residual Attention U-Net (MIRAU-Net) in this work. It integrates residual inception modules with attention gates into U-Net to further enhance brain tumor segmentation performance. Encoder–decoder is connected in this architecture through Inception Residual pathways to decrease the distance between their maps of features. We use the weight cross-entropy and generalized Dice (GDL) with focal Tversky loss functions to resolve the class imbalance problem. The evaluation performance of MIRAU-Net checked with Brats 2019 and obtained mean dice similarities of 0.885 for the whole tumor, 0.879 for the core area, and 0.818 for the enhancement tumor. Experiment results reveal that the suggested MIRAU-Net beats its baselines and provides better efficiency than recent techniques for brain tumor segmentation.
ArticleNumber 116553
Author Piao, Songhao
Noor, Alam
AboElenein, Nagwa M.
Ahmed, Pir Noman
Author_xml – sequence: 1
  givenname: Nagwa M.
  orcidid: 0000-0002-5485-3012
  surname: AboElenein
  fullname: AboElenein, Nagwa M.
  organization: School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
– sequence: 2
  givenname: Songhao
  surname: Piao
  fullname: Piao, Songhao
  email: piaosh@hit.edu.cn
  organization: School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
– sequence: 3
  givenname: Alam
  orcidid: 0000-0002-0077-6509
  surname: Noor
  fullname: Noor, Alam
  organization: CISTER Research Centre, ISEP, Politécnico do Porto, Portugal
– sequence: 4
  givenname: Pir Noman
  surname: Ahmed
  fullname: Ahmed, Pir Noman
  organization: School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
BookMark eNqFkMtKAzEUhoNUsK0-gZsB1zPmMplMBBeleClYBbHrkJk5U1LbpCbTim9v2nHlQlcHDv93Lt8IDayzgNAlwRnBpLheZWajl5BRTElGSME5O0FDUgqZ0kKIARpiSVnKZcHP0CiEFcaY5lgO0Xw-e50s0mfobpKJTcxm690emsTCzut1LN2n8-9JpUNsOpsco0nrfLJcG7fRIQmw3IDtdGecPUenrV4HuPipY7S4v3ubPqZPLw-z6eQprXPMu1SKltG8KrisGGUNZrjWnEpRSCJBQ1XpVuiSkpqXuhF5IzDFRV4BxG4jRMPG6KqfG6_92EHo1MrtvI0rFS1YiQWPBmJK9qnauxA8tKo2_Z2d12atCFYHe2qljvbUwZ7q7UWW_WK3Pqb81z_UbU9BfH5vwKtQG7A1NMZD3anGmT_5b3QUioo
CitedBy_id crossref_primary_10_3390_aerospace11120961
crossref_primary_10_1007_s11063_022_10959_7
crossref_primary_10_3390_bioengineering10060629
crossref_primary_10_1016_j_compbiomed_2022_105693
crossref_primary_10_1016_j_image_2024_117197
crossref_primary_10_1038_s41598_024_77196_x
crossref_primary_10_3788_LOP242385
crossref_primary_10_1038_s41598_024_84386_0
crossref_primary_10_1080_15368378_2023_2299212
crossref_primary_10_1016_j_bspc_2025_107855
crossref_primary_10_1007_s12559_023_10168_x
Cites_doi 10.1109/TPAMI.2015.2408351
10.1109/ICCV.2015.123
10.1186/s12880-015-0068-x
10.1109/ACCESS.2020.2983075
10.1109/CVPR.2017.683
10.1109/CVPR.2014.81
10.1109/CVPR.2018.00745
10.1016/j.media.2016.05.004
10.3389/fncom.2019.00044
10.3389/fncom.2020.00010
10.1109/CVPR.2016.90
10.1109/ACCESS.2020.2998601
10.1097/PDM.0b013e31818f071b
10.1109/ACCESS.2019.2927433
10.1016/j.compbiomed.2019.03.014
10.1016/j.media.2017.10.002
ContentType Journal Article
Copyright 2021
Copyright Elsevier BV Feb 2022
Copyright_xml – notice: 2021
– notice: Copyright Elsevier BV Feb 2022
DBID AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1016/j.image.2021.116553
DatabaseName CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Technology Research Database
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
Computer Science
EISSN 1879-2677
ExternalDocumentID 10_1016_j_image_2021_116553
S0923596521002733
GroupedDBID --K
--M
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
5VS
7-5
71M
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABFNM
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG9
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
WUQ
XPP
ZMT
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ADNMO
AEIPS
AFJKZ
AGQPQ
AIIUN
ANKPU
APXCP
CITATION
EFKBS
~HD
7SC
7SP
8FD
AFXIZ
AGCQF
AGRNS
BNPGV
JQ2
L7M
L~C
L~D
SSH
ID FETCH-LOGICAL-c405t-97f324b659b323d030ca52976919eaebbaf7a821c58ad74d702064bee7a8d77d3
ISICitedReferencesCount 19
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000724345500014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0923-5965
IngestDate Fri Jul 25 07:18:39 EDT 2025
Sat Nov 29 07:11:23 EST 2025
Tue Nov 18 22:04:23 EST 2025
Fri Feb 23 02:41:27 EST 2024
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Brain tumor segmentation
Inception
Residual Module
Full convolutional network
U-Net
Attention Gate
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c405t-97f324b659b323d030ca52976919eaebbaf7a821c58ad74d702064bee7a8d77d3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-0077-6509
0000-0002-5485-3012
OpenAccessLink http://hdl.handle.net/10400.22/21640
PQID 2638075553
PQPubID 2045400
ParticipantIDs proquest_journals_2638075553
crossref_citationtrail_10_1016_j_image_2021_116553
crossref_primary_10_1016_j_image_2021_116553
elsevier_sciencedirect_doi_10_1016_j_image_2021_116553
PublicationCentury 2000
PublicationDate 2022-02-01
PublicationDateYYYYMMDD 2022-02-01
PublicationDate_xml – month: 02
  year: 2022
  text: 2022-02-01
  day: 01
PublicationDecade 2020
PublicationPlace Amsterdam
PublicationPlace_xml – name: Amsterdam
PublicationTitle Signal processing. Image communication
PublicationYear 2022
Publisher Elsevier B.V
Elsevier BV
Publisher_xml – name: Elsevier B.V
– name: Elsevier BV
References Havaei, Davy, Warde-Farley, Biard (b4) 2017
Szegedy, Ioffe (b13) 2017
Kermi, Mahmoudi, Khadir (b23) 2018
Taha, Hanbury (b21) 2015; 37
K. He, X. Zhang, S. Ren, Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, in: Proceedings of the IEEE international conference on computer vision, 2015, pp. 1026–1034.
F. Wang, M. Jiang, C. Qian, S. Yang, Residual attention network for image classification, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 3156–3164.
O. Oktay, J. Schlemper, L.L. Folgoc, et al. Attention u-net: Learning where to look for the pancreas, arXiv preprint
Yang, Zhang, Guldner, Zhang, Chen (b1) 2016
Cahall, Rasool, Bouaynaya, Fathallah-Shaykh (b9) 2019; 13
J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132–7141.
Sudre, Li, Vercauteren (b17) 2017
Li, Li, Wang (b32) 2019; 108
Baid, Talbar, Rane, Gupta, Thakur, Moiyadi (b25) 2020; 14
0000.
A. TensorFlow, A System for Large-Scale Machine Learning This paper is included in the Proceedings of the TensorFlow: A system for large-scale machine learning, in: Proc 12th USENIX Conf. Oper. Syst. Des. Implement, 2016.
Shaikh, Anand, Acharya, Amrutkar (b8) 2017
Chen, Liu, Peng (b28) 2018
Zhao, Wu, Song (b27) 2018; 43
Ronneberger, Fischer, Brox (b6) 2015
Jadon, Leary, Pan, Harder (b18) 2020
Chandra, Vakalopoulou, Fidon, Battistella, Robert (b31) 2018
Castells, García-Gómez, Navarro, Acebes (b2) 2009; 18
Taha, Hanbury (b20) 2015; 15
Lu, Gao, Piao (b16) 2019
Zhang, Jiang, Dong, Hou (b12) 2020; 8
Aboelenein, Songhao, Koubaa, Noor, Afifi (b22) 2020; 8
Frey, Nau (b26) 2019
Islam, Ren (b29) 2017
Hu, Xia (b30) 2017
R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580–587.
K. He, X. Zhang, S. Ren, Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
Hu, Gan, Zhang, Deng, Xiao, Huang, Cao, Gao (b24) 2019; 7
Shen, Wang, Zhang, McKenna (b5) 2017
10.1016/j.image.2021.116553_b14
Sudre (10.1016/j.image.2021.116553_b17) 2017
10.1016/j.image.2021.116553_b15
Cahall (10.1016/j.image.2021.116553_b9) 2019; 13
Yang (10.1016/j.image.2021.116553_b1) 2016
10.1016/j.image.2021.116553_b19
Zhang (10.1016/j.image.2021.116553_b12) 2020; 8
Chandra (10.1016/j.image.2021.116553_b31) 2018
Taha (10.1016/j.image.2021.116553_b20) 2015; 15
Zhao (10.1016/j.image.2021.116553_b27) 2018; 43
Kermi (10.1016/j.image.2021.116553_b23) 2018
Taha (10.1016/j.image.2021.116553_b21) 2015; 37
10.1016/j.image.2021.116553_b7
Hu (10.1016/j.image.2021.116553_b24) 2019; 7
Castells (10.1016/j.image.2021.116553_b2) 2009; 18
Havaei (10.1016/j.image.2021.116553_b4) 2017
Hu (10.1016/j.image.2021.116553_b30) 2017
10.1016/j.image.2021.116553_b3
Shaikh (10.1016/j.image.2021.116553_b8) 2017
Aboelenein (10.1016/j.image.2021.116553_b22) 2020; 8
Islam (10.1016/j.image.2021.116553_b29) 2017
Frey (10.1016/j.image.2021.116553_b26) 2019
Baid (10.1016/j.image.2021.116553_b25) 2020; 14
Li (10.1016/j.image.2021.116553_b32) 2019; 108
Szegedy (10.1016/j.image.2021.116553_b13) 2017
Jadon (10.1016/j.image.2021.116553_b18) 2020
Lu (10.1016/j.image.2021.116553_b16) 2019
Chen (10.1016/j.image.2021.116553_b28) 2018
10.1016/j.image.2021.116553_b10
Shen (10.1016/j.image.2021.116553_b5) 2017
Ronneberger (10.1016/j.image.2021.116553_b6) 2015
10.1016/j.image.2021.116553_b11
References_xml – start-page: 388
  year: 2019
  end-page: 396
  ident: b26
  article-title: Memory efficient brain tumor segmentation using an autoencoder-regularized U-net
  publication-title: International MICCAI Brainlesion Workshop
– reference: O. Oktay, J. Schlemper, L.L. Folgoc, et al. Attention u-net: Learning where to look for the pancreas, arXiv preprint
– reference: K. He, X. Zhang, S. Ren, Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
– start-page: 309
  year: 2017
  end-page: 319
  ident: b8
  article-title: Brain tumor segmentation using dense fully convolutional neural network
  publication-title: International MICCAI Brainlesion Workshop
– reference: R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580–587.
– start-page: 433
  year: 2017
  end-page: 441
  ident: b5
  article-title: Boundary-aware fully convolutional network for brain tumor segmentation
  publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention
– start-page: 230
  year: 2019
  end-page: 233
  ident: b16
  article-title: Dynamic weighted cross entropy for semantic segmentation with extremely imbalanced data
  publication-title: 2019 International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM)
– volume: 8
  start-page: 101406
  year: 2020
  end-page: 101415
  ident: b22
  article-title: HTTU-Net: Hybrid two track U-net for automatic brain tumor segmentation
  publication-title: IEEE Access
– volume: 108
  start-page: 150
  year: 2019
  end-page: 160
  ident: b32
  article-title: A novel end-to-end brain tumor segmentation method using improved fully convolutional networks
  publication-title: Comput. Biol. Med.
– volume: 13
  start-page: 44
  year: 2019
  ident: b9
  article-title: Inception modules enhance brain tumor segmentation
  publication-title: Front. Comput. Neurosci.
– volume: 18
  start-page: 206
  year: 2009
  end-page: 218
  ident: b2
  article-title: Automated brain tumor biopsy prediction using single-labeling cDNA microarrays-based gene expression profiling
  publication-title: Diagn. Mol. Pathol.
– year: 2017
  ident: b13
  article-title: Inception-v4, inception-resnet and the impact of residual connections on learning
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31
– start-page: 113180Q
  year: 2020
  ident: b18
  article-title: A comparative study of 2D image segmentation algorithms for traumatic brain lesions using CT data from the protectiii multicenter clinical trial
  publication-title: Medical Imaging 2020: Imaging Informatics for Healthcare, Research, and Applications, Vol. 11318
– reference: A. TensorFlow, A System for Large-Scale Machine Learning This paper is included in the Proceedings of the TensorFlow: A system for large-scale machine learning, in: Proc 12th USENIX Conf. Oper. Syst. Des. Implement, 2016.
– start-page: 423
  year: 2017
  end-page: 434
  ident: b30
  article-title: 3D deep neural network-based brain tumor segmentation using multimodality magnetic resonance sequences
  publication-title: International MIC-CAI Brainlesion Workshop
– reference: F. Wang, M. Jiang, C. Qian, S. Yang, Residual attention network for image classification, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 3156–3164.
– start-page: 18
  year: 2017
  end-page: 31
  ident: b4
  article-title: Brain tumor segmentation with deep neural networks
  publication-title: Med. Image Anal.
– volume: 37
  start-page: 2153
  year: 2015
  end-page: 2163
  ident: b21
  article-title: An efficient algorithm for calculating the exact hausdorff distance
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 240
  year: 2017
  end-page: 248
  ident: b17
  article-title: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations
  publication-title: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support
– reference: J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132–7141.
– volume: 7
  start-page: 92615
  year: 2019
  end-page: 92629
  ident: b24
  article-title: Brain tumor segmentation using multi-cascaded convolutional neural networks and conditional random field
  publication-title: IEEE Access
– start-page: 298
  year: 2017
  end-page: 308
  ident: b29
  article-title: Multi-modal pixelnet for brain tumor segmentation
  publication-title: International MICCAI Brainlesion Workshop
– start-page: 320234
  year: 2015
  end-page: 320241
  ident: b6
  article-title: U-net:Convolutional networks for biomedical image segmentation
  publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention
– volume: 14
  start-page: 10
  year: 2020
  ident: b25
  article-title: A novel approach for fully automatic intra-tumor segmentation with 3D U-net architecture for gliomas
  publication-title: Front. Comput. Neurosci.
– volume: 15
  start-page: 1
  year: 2015
  end-page: 28
  ident: b20
  article-title: Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool
  publication-title: BMC Med. Imaging
– start-page: 299
  year: 2018
  end-page: 310
  ident: b31
  article-title: Context aware 3D CNNs for brain tumor segmentation
  publication-title: International MICCAI Brainlesion Workshop
– volume: 8
  start-page: 58533
  year: 2020
  end-page: 58545
  ident: b12
  article-title: Attention gate resu-net for automatic MRI brain tumor segmentation
  publication-title: IEEE Access
– reference: K. He, X. Zhang, S. Ren, Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, in: Proceedings of the IEEE international conference on computer vision, 2015, pp. 1026–1034.
– start-page: 358
  year: 2018
  end-page: 368
  ident: b28
  article-title: S3D-unet: separable 3D U-net for brain tumor segmentation
  publication-title: International MICCAI Brainlesion Workshop
– volume: 43
  start-page: 98
  year: 2018
  end-page: 111
  ident: b27
  article-title: A deep learning model integrating FCNNs and CRFs for brain tumor segmentation
  publication-title: Med. Image Anal.
– reference: , 0000.
– start-page: 658
  year: 2016
  end-page: 666
  ident: b1
  article-title: 3D segmentation of glial cells using fully convolutional networks and k-terminal cut
  publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention
– start-page: 37
  year: 2018
  end-page: 48
  ident: b23
  article-title: Deep convolutional neural networks using U-net for automatic brain tumor segmentation in multimodal MRI volumes
  publication-title: International MICCAI Brainlesion Workshop
– volume: 37
  start-page: 2153
  issue: 11
  year: 2015
  ident: 10.1016/j.image.2021.116553_b21
  article-title: An efficient algorithm for calculating the exact hausdorff distance
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2015.2408351
– start-page: 230
  year: 2019
  ident: 10.1016/j.image.2021.116553_b16
  article-title: Dynamic weighted cross entropy for semantic segmentation with extremely imbalanced data
– start-page: 423
  year: 2017
  ident: 10.1016/j.image.2021.116553_b30
  article-title: 3D deep neural network-based brain tumor segmentation using multimodality magnetic resonance sequences
– start-page: 309
  year: 2017
  ident: 10.1016/j.image.2021.116553_b8
  article-title: Brain tumor segmentation using dense fully convolutional neural network
– start-page: 37
  year: 2018
  ident: 10.1016/j.image.2021.116553_b23
  article-title: Deep convolutional neural networks using U-net for automatic brain tumor segmentation in multimodal MRI volumes
– ident: 10.1016/j.image.2021.116553_b14
  doi: 10.1109/ICCV.2015.123
– volume: 15
  start-page: 1
  issue: 1
  year: 2015
  ident: 10.1016/j.image.2021.116553_b20
  article-title: Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool
  publication-title: BMC Med. Imaging
  doi: 10.1186/s12880-015-0068-x
– volume: 8
  start-page: 58533
  year: 2020
  ident: 10.1016/j.image.2021.116553_b12
  article-title: Attention gate resu-net for automatic MRI brain tumor segmentation
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.2983075
– ident: 10.1016/j.image.2021.116553_b10
  doi: 10.1109/CVPR.2017.683
– ident: 10.1016/j.image.2021.116553_b15
– year: 2017
  ident: 10.1016/j.image.2021.116553_b13
  article-title: Inception-v4, inception-resnet and the impact of residual connections on learning
– ident: 10.1016/j.image.2021.116553_b19
– start-page: 388
  year: 2019
  ident: 10.1016/j.image.2021.116553_b26
  article-title: Memory efficient brain tumor segmentation using an autoencoder-regularized U-net
– start-page: 433
  year: 2017
  ident: 10.1016/j.image.2021.116553_b5
  article-title: Boundary-aware fully convolutional network for brain tumor segmentation
– ident: 10.1016/j.image.2021.116553_b3
  doi: 10.1109/CVPR.2014.81
– ident: 10.1016/j.image.2021.116553_b11
  doi: 10.1109/CVPR.2018.00745
– start-page: 320234
  year: 2015
  ident: 10.1016/j.image.2021.116553_b6
  article-title: U-net:Convolutional networks for biomedical image segmentation
– start-page: 18
  year: 2017
  ident: 10.1016/j.image.2021.116553_b4
  article-title: Brain tumor segmentation with deep neural networks
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2016.05.004
– start-page: 298
  year: 2017
  ident: 10.1016/j.image.2021.116553_b29
  article-title: Multi-modal pixelnet for brain tumor segmentation
– volume: 13
  start-page: 44
  year: 2019
  ident: 10.1016/j.image.2021.116553_b9
  article-title: Inception modules enhance brain tumor segmentation
  publication-title: Front. Comput. Neurosci.
  doi: 10.3389/fncom.2019.00044
– start-page: 240
  year: 2017
  ident: 10.1016/j.image.2021.116553_b17
  article-title: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations
– start-page: 658
  year: 2016
  ident: 10.1016/j.image.2021.116553_b1
  article-title: 3D segmentation of glial cells using fully convolutional networks and k-terminal cut
– start-page: 299
  year: 2018
  ident: 10.1016/j.image.2021.116553_b31
  article-title: Context aware 3D CNNs for brain tumor segmentation
– volume: 14
  start-page: 10
  year: 2020
  ident: 10.1016/j.image.2021.116553_b25
  article-title: A novel approach for fully automatic intra-tumor segmentation with 3D U-net architecture for gliomas
  publication-title: Front. Comput. Neurosci.
  doi: 10.3389/fncom.2020.00010
– ident: 10.1016/j.image.2021.116553_b7
  doi: 10.1109/CVPR.2016.90
– volume: 8
  start-page: 101406
  year: 2020
  ident: 10.1016/j.image.2021.116553_b22
  article-title: HTTU-Net: Hybrid two track U-net for automatic brain tumor segmentation
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.2998601
– volume: 18
  start-page: 206
  issue: 4
  year: 2009
  ident: 10.1016/j.image.2021.116553_b2
  article-title: Automated brain tumor biopsy prediction using single-labeling cDNA microarrays-based gene expression profiling
  publication-title: Diagn. Mol. Pathol.
  doi: 10.1097/PDM.0b013e31818f071b
– volume: 7
  start-page: 92615
  year: 2019
  ident: 10.1016/j.image.2021.116553_b24
  article-title: Brain tumor segmentation using multi-cascaded convolutional neural networks and conditional random field
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2927433
– volume: 108
  start-page: 150
  year: 2019
  ident: 10.1016/j.image.2021.116553_b32
  article-title: A novel end-to-end brain tumor segmentation method using improved fully convolutional networks
  publication-title: Comput. Biol. Med.
  doi: 10.1016/j.compbiomed.2019.03.014
– start-page: 113180Q
  year: 2020
  ident: 10.1016/j.image.2021.116553_b18
  article-title: A comparative study of 2D image segmentation algorithms for traumatic brain lesions using CT data from the protectiii multicenter clinical trial
– volume: 43
  start-page: 98
  year: 2018
  ident: 10.1016/j.image.2021.116553_b27
  article-title: A deep learning model integrating FCNNs and CRFs for brain tumor segmentation
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2017.10.002
– start-page: 358
  year: 2018
  ident: 10.1016/j.image.2021.116553_b28
  article-title: S3D-unet: separable 3D U-net for brain tumor segmentation
SSID ssj0002409
Score 2.4255428
Snippet Gliomas are the largest prevalent and destructive of brain tumors and have crucial parts for the diagnosing and treating of MRI brain tumors during...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 116553
SubjectTerms Attention Gate
Brain
Brain cancer
Brain tumor segmentation
Coders
Full convolutional network
Image segmentation
Inception
Neural networks
Performance evaluation
Residual Module
Tumors
U-Net
Title MIRAU-Net: An improved neural network based on U-Net for gliomas segmentation
URI https://dx.doi.org/10.1016/j.image.2021.116553
https://www.proquest.com/docview/2638075553
Volume 101
WOSCitedRecordID wos000724345500014&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: 1879-2677
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002409
  issn: 0923-5965
  databaseCode: AIEXJ
  dateStart: 19950201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lj9MwELZKlwMceCysWFiQD4hLcUWcJo65VagrirqhYlvUW-QkTjarNi1tWfZn8JMZP5JmeVRw4BJVjuOmnunMN-N5IPSSJVw4fuKTIOM-6QVUEs6zmIgUwELsZlQ4OlF4xMIwmM34uNX6XuXCXM1ZWQbX13z1X0kNY0BslTr7D-SuF4UB-AxEhyuQHa5_Rfiz4af-lISy8vkV2m2gTvmlLrFRmsDvjtJfqTor0JN1uGE-L1S4UGcj84XNSSqb6PW8yBV4XZnkAtVyoTNcqKCfpJlm0jhRGoBOs900Q5F_Ezvf67gQ2kl7vizzC7GsfdJL4z7oz8WiXudiYTyy42LdCeEFy6arAqzcNzfCPnY5NJ-bfkjqEo-bhhFdaaRwwDihvu3vUolpu5IRtM5vxb_xRFx2C_XbwfinTleVFzLliG8W2w4_RqfT0SiaDGaTV6svRPUhU-f1tinLLXRAmceDNjroDwezD7V2BwRk6jfa164qWemYwV--909o5ye9r8HM5AG6Z60Q3Dfc8xC1ZHmI7luLBFt5v4GhqulHNXaI7jYqWD5CZzW3vcX9Ele8hg2vYctrWPMaXpZYT8XAa9jyGm7y2mM0PR1M3r0ntkMHSQDobwlnGQDy2Pd47FI3BYWRCI8CwuUOl0LGsciYCKiTeIFIWS9lYJz4vVhKGE0ZS90j1C6XpXyCsMgkbG0mwWLPer6TilTEEtbMHMcFMdM7RrTaySix5etVF5V5VMUpXkZ6-yO1_ZHZ_mP0un5oZaq37J_uVySKLAA1wDICBtv_4ElF0MiKgk1EfdXMwYPbT_fffobu7P4tJ6i9XX-Vz9Ht5GpbbNYvLAP-AJbirbc
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=MIRAU-Net%3A+An+improved+neural+network+based+on+U-Net+for+gliomas+segmentation&rft.jtitle=Signal+processing.+Image+communication&rft.au=AboElenein%2C+Nagwa+M&rft.au=Piao%2C+Songhao&rft.au=Noor%2C+Alam&rft.au=Ahmed%2C+Pir+Noman&rft.date=2022-02-01&rft.pub=Elsevier+BV&rft.issn=0923-5965&rft.eissn=1879-2677&rft.volume=101&rft.spage=1&rft_id=info:doi/10.1016%2Fj.image.2021.116553&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0923-5965&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0923-5965&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0923-5965&client=summon