Hybrid deep autoencoder network based adaptive cross guided bilateral filter for motion artifacts correction and denoising from MRI

Removal of motion artifacts from medical images is essential, because the respiration by patient causes degradation in artifact removal. Therefore, getting an MRI without any artifacts and noise is challenging. Previous techniques failed to preserve the image quality during denoising, thereby affect...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The imaging science journal Jg. ahead-of-print; H. ahead-of-print; S. 1 - 16
Hauptverfasser: Samuel, Shiju, Ochawar, Rohini S., Rukmini, M.S.S.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Taylor & Francis 02.01.2024
Schlagworte:
ISSN:1368-2199, 1743-131X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Removal of motion artifacts from medical images is essential, because the respiration by patient causes degradation in artifact removal. Therefore, getting an MRI without any artifacts and noise is challenging. Previous techniques failed to preserve the image quality during denoising, thereby affecting the classification accuracy. To overcome such challenges, two modules are considered in this work: classification and denoising. The classification process is successfully performed by Hybrid Deep autoencoder-convolutional neural network (DAE-CNN). It classifies the original images into motion artifacts, available and normal images. Then, the available artifacts are removed using cross guided bilateral filter (CGBF). The optimal parameters required to improve the CGBF performance are selected using the hybrid optimization algorithm. The filter's performance relies on the optimal spatial and range kernels selection. Finally, the classification and denoising-based results are evaluated using the BRATS 2015 dataset and achieved 95.84% accuracy and PSNR - 46.4, which is better than existing methods.
AbstractList Removal of motion artifacts from medical images is essential, because the respiration by patient causes degradation in artifact removal. Therefore, getting an MRI without any artifacts and noise is challenging. Previous techniques failed to preserve the image quality during denoising, thereby affecting the classification accuracy. To overcome such challenges, two modules are considered in this work: classification and denoising. The classification process is successfully performed by Hybrid Deep autoencoder-convolutional neural network (DAE-CNN). It classifies the original images into motion artifacts, available and normal images. Then, the available artifacts are removed using cross guided bilateral filter (CGBF). The optimal parameters required to improve the CGBF performance are selected using the hybrid optimization algorithm. The filter's performance relies on the optimal spatial and range kernels selection. Finally, the classification and denoising-based results are evaluated using the BRATS 2015 dataset and achieved 95.84% accuracy and PSNR - 46.4, which is better than existing methods.
Author Samuel, Shiju
Ochawar, Rohini S.
Rukmini, M.S.S.
Author_xml – sequence: 1
  givenname: Shiju
  surname: Samuel
  fullname: Samuel, Shiju
  email: shijuvector@gmail.com
  organization: Technology & Research
– sequence: 2
  givenname: Rohini S.
  surname: Ochawar
  fullname: Ochawar, Rohini S.
  organization: Shri Ramdeobaba College of Engineering & Management
– sequence: 3
  givenname: M.S.S.
  surname: Rukmini
  fullname: Rukmini, M.S.S.
  organization: Technology & Research
BookMark eNqFkE1LAzEQhoNUsK3-BCF_YGuy2d3u4kUpagsVQRS8hdl8lOg2KUmq9OwfN2vrxYOe5mVm3vl4RmhgnVUInVMyoaQmF5RVdU6bZpKTnE2SqoqmOEJDOi1YRhl9GSSderK-6QSNQnglJBWLaog-57vWG4mlUhsM2-iUFU4qj62KH86_4RaCkhgkbKJ5V1h4FwJebY1M2dZ0EJWHDmvTJYG183jtonEWg49Gg4gBC-e9Evuk7TdZZ4KxK6y9W-P7x8UpOtbQBXV2iGP0fHvzNJtny4e7xex6mQlGSczyuhaVlCVpyooBq2sAKKAplFCaMVqoKpcwLcoWREPKmhGYKpLnhDZA2kZqNkaX-7nfT3iluTAR-sOiB9NxSnjPk__w5D1PfuCZ3OUv98abNfjdv76rvc_YhGcNiWoneYRd57z2YIUJnP094guE25G6
CitedBy_id crossref_primary_10_1002_ima_70106
Cites_doi 10.1016/j.mri.2019.05.038
10.1016/j.zemedi.2018.11.002
10.1155/2022/5906877
10.1016/j.neuroimage.2021.117756
10.1109/TMI.2014.2377694
10.1038/s41597-021-01044-0
10.1002/mrm.27705
10.3174/ajnr.A6436
10.1016/j.mri.2019.05.020
10.1007/s10278-018-0110-y
10.1007/s11760-013-0556-9
10.1109/JSEN.2018.2870759
10.1088/0031-9155/61/5/R32
10.3390/app12105097
10.1002/mrm.24314
10.1002/jmri.24850
10.1016/j.mri.2020.05.004
10.1016/j.asoc.2016.02.043
10.1186/s12968-017-0425-8
10.3174/ajnr.A4996
10.1016/j.jneumeth.2017.07.031
10.1038/s41598-019-56847-4
10.1002/mrm.27783
10.1016/j.ijleo.2017.12.074
10.1109/TMI.2017.2737081
10.1007/s10334-017-0650-z
10.1002/mrm.27771
10.1002/mrm.10093
10.1002/mrm.27772
10.1109/TMI.2021.3073381
10.1109/TIP.2015.2389617
10.1016/j.advengsoft.2017.07.002
10.1016/j.neuroimage.2017.08.025
10.1016/j.media.2014.05.005
ContentType Journal Article
Copyright 2023 The Royal Photographic Society 2023
Copyright_xml – notice: 2023 The Royal Photographic Society 2023
DBID AAYXX
CITATION
DOI 10.1080/13682199.2023.2196494
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Visual Arts
EISSN 1743-131X
EndPage 16
ExternalDocumentID 10_1080_13682199_2023_2196494
2196494
Genre Research Article
GroupedDBID 002
0BK
0R~
1~B
29I
4.4
53G
AAGDL
AAHIA
AAJMT
AALDU
AAMIU
AAPUL
AAQRR
ABCCY
ABDBF
ABFIM
ABJNI
ABLIJ
ABPAQ
ABXUL
ABXYU
ACFOO
ACGFS
ACTIO
ACUHS
ADCVX
ADGTB
ADMLS
AEISY
AENEX
AEYOC
AFRVT
AGDLA
AHDZW
AIJEM
AIYEW
AKBVH
AKOOK
ALMA_UNASSIGNED_HOLDINGS
ALQZU
AQRUH
AQTUD
AWYRJ
BLEHA
CCCUG
DGEBU
DU5
E01
EAP
EBS
EMK
EPL
EST
ESX
H13
HCLVR
HZ~
I-F
KYCEM
LJTGL
M4Z
MV1
P2P
P75
P7B
RIG
RNANH
ROSJB
RTWRZ
TASJS
TBQAZ
TCY
TDBHL
TEX
TFL
TFT
TFW
TTHFI
TUROJ
TUS
WH7
ZGOLN
AAYXX
CITATION
ID FETCH-LOGICAL-c310t-288c6dd509563a388aaa4a94ecef3314e62da745bac905830a7e022019a0b9df3
IEDL.DBID TFW
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000970741100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1368-2199
IngestDate Sat Nov 29 03:42:03 EST 2025
Tue Nov 18 21:05:14 EST 2025
Mon Oct 20 23:46:11 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue ahead-of-print
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c310t-288c6dd509563a388aaa4a94ecef3314e62da745bac905830a7e022019a0b9df3
PageCount 16
ParticipantIDs crossref_citationtrail_10_1080_13682199_2023_2196494
informaworld_taylorfrancis_310_1080_13682199_2023_2196494
crossref_primary_10_1080_13682199_2023_2196494
PublicationCentury 2000
PublicationDate 2024-01-02
PublicationDateYYYYMMDD 2024-01-02
PublicationDate_xml – month: 01
  year: 2024
  text: 2024-01-02
  day: 02
PublicationDecade 2020
PublicationTitle The imaging science journal
PublicationYear 2024
Publisher Taylor & Francis
Publisher_xml – name: Taylor & Francis
References e_1_3_2_27_1
e_1_3_2_28_1
Johnson PM (e_1_3_2_22_1) 2019; 82
e_1_3_2_29_1
e_1_3_2_42_1
e_1_3_2_20_1
e_1_3_2_41_1
e_1_3_2_21_1
e_1_3_2_23_1
e_1_3_2_24_1
e_1_3_2_25_1
e_1_3_2_26_1
e_1_3_2_40_1
Elhoseny M (e_1_3_2_36_1) 2019; 143
e_1_3_2_16_1
e_1_3_2_9_1
e_1_3_2_17_1
e_1_3_2_8_1
Manoharan H (e_1_3_2_39_1) 2022
e_1_3_2_7_1
e_1_3_2_19_1
Kshirsagar PR (e_1_3_2_38_1) 2022
e_1_3_2_2_1
e_1_3_2_31_1
e_1_3_2_10_1
e_1_3_2_33_1
e_1_3_2_11_1
e_1_3_2_32_1
e_1_3_2_6_1
e_1_3_2_12_1
e_1_3_2_35_1
e_1_3_2_5_1
e_1_3_2_13_1
e_1_3_2_34_1
e_1_3_2_4_1
e_1_3_2_14_1
e_1_3_2_37_1
Patel S (e_1_3_2_3_1) 2016; 6
e_1_3_2_15_1
Fantini I (e_1_3_2_18_1) 2018
Alsattar HA (e_1_3_2_30_1) 2019
References_xml – ident: e_1_3_2_19_1
  doi: 10.1016/j.mri.2019.05.038
– ident: e_1_3_2_17_1
  doi: 10.1016/j.zemedi.2018.11.002
– ident: e_1_3_2_37_1
  doi: 10.1155/2022/5906877
– ident: e_1_3_2_31_1
  doi: 10.1016/j.neuroimage.2021.117756
– ident: e_1_3_2_32_1
  doi: 10.1109/TMI.2014.2377694
– start-page: 1424
  year: 2022
  ident: e_1_3_2_38_1
  article-title: Perception exploration on robustness syndromes with pre-processing entities using machine learning algorithm
  publication-title: Front Public Health
– ident: e_1_3_2_42_1
  doi: 10.1038/s41597-021-01044-0
– ident: e_1_3_2_9_1
  doi: 10.1002/mrm.27705
– ident: e_1_3_2_13_1
  doi: 10.3174/ajnr.A6436
– ident: e_1_3_2_8_1
  doi: 10.1016/j.mri.2019.05.020
– ident: e_1_3_2_26_1
  doi: 10.1007/s10278-018-0110-y
– ident: e_1_3_2_27_1
  doi: 10.1007/s11760-013-0556-9
– ident: e_1_3_2_16_1
  doi: 10.1109/JSEN.2018.2870759
– ident: e_1_3_2_15_1
  doi: 10.1088/0031-9155/61/5/R32
– ident: e_1_3_2_40_1
  doi: 10.3390/app12105097
– ident: e_1_3_2_12_1
  doi: 10.1002/mrm.24314
– ident: e_1_3_2_2_1
  doi: 10.1002/jmri.24850
– ident: e_1_3_2_11_1
  doi: 10.1016/j.mri.2020.05.004
– start-page: 10
  year: 2022
  ident: e_1_3_2_39_1
  article-title: Deep conviction systems for biomedical applications using intuiting procedures With cross point approach
  publication-title: Front Public Health
– ident: e_1_3_2_34_1
  doi: 10.1016/j.asoc.2016.02.043
– ident: e_1_3_2_5_1
  doi: 10.1186/s12968-017-0425-8
– ident: e_1_3_2_24_1
  doi: 10.3174/ajnr.A4996
– volume: 143
  start-page: 125
  year: 2019
  ident: e_1_3_2_36_1
  article-title: Optimal bilateral filter and convolutional neural network based denoising method of medical image measurements
  publication-title: Measurement ( Mahwah N J)
– start-page: 1
  year: 2018
  ident: e_1_3_2_18_1
  article-title: Automatic detection of motion artifacts on MRI using Deep CNN
  publication-title: Pattern Recognition in Neuroimaging (PRNI) IEEE
– ident: e_1_3_2_7_1
  doi: 10.1016/j.jneumeth.2017.07.031
– ident: e_1_3_2_4_1
  doi: 10.1038/s41598-019-56847-4
– ident: e_1_3_2_20_1
  doi: 10.1002/mrm.27783
– ident: e_1_3_2_23_1
– ident: e_1_3_2_35_1
  doi: 10.1016/j.ijleo.2017.12.074
– ident: e_1_3_2_6_1
  doi: 10.1109/TMI.2017.2737081
– volume: 6
  start-page: 53
  issue: 1
  year: 2016
  ident: e_1_3_2_3_1
  article-title: Survey of data mining techniques used in healthcare domain
  publication-title: Int J Inf
– start-page: 1
  year: 2019
  ident: e_1_3_2_30_1
  article-title: Novel meta-heuristic bald eagle search optimization algorithm
  publication-title: Artif Intell Rev
– ident: e_1_3_2_14_1
  doi: 10.1007/s10334-017-0650-z
– ident: e_1_3_2_25_1
  doi: 10.1002/mrm.27771
– ident: e_1_3_2_33_1
  doi: 10.1002/mrm.10093
– volume: 82
  start-page: 901
  issue: 3
  year: 2019
  ident: e_1_3_2_22_1
  article-title: Conditional generative adversarial network for 3D rigid-body motion correction in MRI
  publication-title: Magn Reson Med
  doi: 10.1002/mrm.27772
– ident: e_1_3_2_41_1
  doi: 10.1109/TMI.2021.3073381
– ident: e_1_3_2_28_1
  doi: 10.1109/TIP.2015.2389617
– ident: e_1_3_2_29_1
  doi: 10.1016/j.advengsoft.2017.07.002
– ident: e_1_3_2_10_1
  doi: 10.1016/j.neuroimage.2017.08.025
– ident: e_1_3_2_21_1
  doi: 10.1016/j.media.2014.05.005
SSID ssj0017446
Score 2.2960248
Snippet Removal of motion artifacts from medical images is essential, because the respiration by patient causes degradation in artifact removal. Therefore, getting an...
SourceID crossref
informaworld
SourceType Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms autoencoder
bald eagle search optimization
cross-guided bilateral filtering
Deep learning
kernel selection
Motion artifact removal
Peak Signal to Noise Ratio (PSNR)
Salp swarm optimization
Title Hybrid deep autoencoder network based adaptive cross guided bilateral filter for motion artifacts correction and denoising from MRI
URI https://www.tandfonline.com/doi/abs/10.1080/13682199.2023.2196494
Volume ahead-of-print
WOSCitedRecordID wos000970741100001&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: PRVAWR
  databaseName: Taylor & Francis Online Journals
  customDbUrl:
  eissn: 1743-131X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017446
  issn: 1368-2199
  databaseCode: TFW
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://www.tandfonline.com
  providerName: Taylor & Francis
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA6yeNCDb3F9kYPXatuk2-Qo4rKCioiPvZVpHlJYusu2K3j2j5tpuuIe1IMeG5g2TWYyyWS-bwg5kZrFqbDambjWgdOQKJA5s0EOSAuZpiE0KP6n6_T2VgyH8q7NJqzatEo8Q1tPFNGs1WjckFfzjLiziPWEMzSEmcTsNEZKKYmMoM71o2k-9J8_7xFS7vFFTiJAkTmG57u3LHinBe7SL16nv_4P_d0ga-2Wk557HdkkS6bcIqtPRTXzrdU2eR-8IXKLamMmFGb1GOkttZnS0meJU3R2moKGCS6PtOk9fZkV2rXmxQgQxzyitsC7d-p-h_rqQBQVE7ETFVVYBkT5xhK_VI4LjFNQBLjQm_urHfLYv3y4GARteYZAuT1hHcRCqJ7WCVIZMmBCAAAHyY0ylrGIm16sIeVJDkqGiWAhpAZxvZGEMJfasl3SKcel2SPUrQLOk7pzemI4N7EVrKclUxxMokIT2S7h82nJVMtdjiU0RlnUUpzOxzjDMc7aMe6S00-xiSfv-E1Afp3zrG6iJtaXOMnYj7L7f5A9ICvukTehnfiQdOrpzByRZfVaF9X0uFHpD1pM8oM
linkProvider Taylor & Francis
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV05T8MwFLa4JGDgRtx4YA0ksdPYI0JUrWg7oFK6RY4PFKlKqzZFYuaP4xenVTsAA6yOXuLY77Cf_X0PoRuuSBgzo6yJK-VZDQk8nhLjpQJoIePYFyWKv9eKOx3W7_NFLAxcq4Q9tHFEEaWvBuOGZPTsStxdQGrMWhrgTEJyGwKnFKeraD2ysRb487v11_lJQkwdwsiKeCAzQ_F895ql-LTEXroQd-q7_9HjPbRTrTrxvVOTfbSi8wO03csmU9c6OUSfjQ8Ab2Gl9QiLaTEEhkulxzh3F8UxxDuFhRIj8JC47D5-m2bKtqbZQACUeYBNBsfv2P4PdgWCMOgmwCcmWEIlEOkac_hSPswgVYEB44Lbz80j9FJ_7D40vKpCgyftsrDwQsZkTakI2AyJIIwJIajgVEttCAmoroVKxDRKheR-xIgvYg3Q3oALP-XKkGO0lg9zfYKwdQQ2mNqteqQp1aFhpKY4kVToSPo6MKeIzuYlkRV9OVTRGCRBxXI6G-MExjipxvgU3c7FRo6_4zcBvjjpSVEmToyrcpKQH2XP_iB7jTYb3XYraTU7T-doyz6iZaYnvEBrxXiqL9GGfC-yyfiq1O8vvoj2rQ
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZ4CcHAG1GeHlgDSewk9oiACkSpEILCFjl-oEhVWjUpEjN_HF-cIjoAA6wXXeLYZ9_Zvu87hI65ImHCjLJTXCnPWkjg8YwYLxNAC5kkvqhR_L1O0u2y52d-12QTlk1aJeyhjSOKqNdqmNxDZSYZcacBiZmdaAAzCclJCJRSnM6ieRs6x2DkD-2nz4uEhDqAkVXxQGcC4vnuNVPuaYq89Ivbaa_-Q4PX0EoTc-IzZyTraEYXG2i5l5djJy030fvVG0C3sNJ6iMW4GgC_pdIjXLg0cQzeTmGhxBDWR1y3Hr-Mc2WlWd4XAGTuY5PD5Tu2v4NdeSAMlgngiRJLqAMinbCALxWDHA4qMCBc8O399RZ6bF8-nF95TX0GT9qgsPJCxmSsVARchkQQxoQQVHCqpTaEBFTHoRIJjTIhuR8x4otEA7A34MLPuDJkG80Vg0LvIGyXAetK7UY90pTq0DASK04kFTqSvg5MC9HJsKSyIS-HGhr9NGg4Tid9nEIfp00ft9DJp9rQsXf8psC_jnla1ccmxtU4ScmPurt_0D1Ci3cX7bRz3b3ZQ0v2Ca2PecJ9NFeNxvoALcjXKi9Hh7V1fwDYavVf
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=Hybrid+deep+autoencoder+network+based+adaptive+cross+guided+bilateral+filter+for+motion+artifacts+correction+and+denoising+from+MRI&rft.jtitle=The+imaging+science+journal&rft.au=Samuel%2C+Shiju&rft.au=Ochawar%2C+Rohini+S.&rft.au=Rukmini%2C+M.S.S.&rft.date=2024-01-02&rft.issn=1368-2199&rft.eissn=1743-131X&rft.volume=72&rft.issue=1&rft.spage=76&rft.epage=91&rft_id=info:doi/10.1080%2F13682199.2023.2196494&rft.externalDBID=n%2Fa&rft.externalDocID=10_1080_13682199_2023_2196494
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1368-2199&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1368-2199&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1368-2199&client=summon